As of October 22, 2026, OpenAI GPT-6 Luna ranks #45 of 123 models overall with 59.7 ±7.7 on the LLMBenchmark Index. GPT-6 Luna ranks #19 of 108 in math, its strongest category. OpenAI GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens. GPT-6 Luna was released on September 22, 2026.
GPT-6 Luna's output price ranks 79 of 349 priced models, counting from the cheapest.
Listed on OpenRouter September 22, 2026, 30 days before our data. Results so far on 103 of 195 public boards; this page updates every day as boards publish.
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...
openai/gpt-6-luna The tick on a coding bar is the median of every model measured on it. Outside coding, the place is this model's rank on that board. A board that never ran the model says so.
Measured in 7 of 7 categories. A place counts only the models measured on that board.
The index averages only the coding benchmarks that have a result; the others are skipped, never filled in. How it is weighted
Not measured on Aider polyglot, SWE-bench Verified, SWE-bench Lite, SWE-bench (full test set), SWE-bench Multimodal, SWE-bench Multilingual, AA Coding Index, LiveCodeBench (Vals AI), Vibe Code Bench 1-100 (Vals AI), SkillsBench (Vals AI), LiveCodeBench (Artificial Analysis run), Terminal-Bench Hard (Artificial Analysis run), Terminal-Bench, DeepSWE, FrontierSWE, GSO-Bench, WeirdML, MirrorCode, Cybench, SciCode
Not measured on AA Agentic Index, Design Arena: agents building Android apps, Design Arena: agents building Godot games, Design Arena: agents building games, Design Arena: HTML slides, Design Arena: PowerPoint slides, Design Arena: spreadsheets, Time Horizon Index (Vals AI), CUA-bench (Vals AI), Robo-bench (Vals AI), τ²-Bench Telecom, METR time horizons, Remote Labor Index, GDPval, OSWorld 2.0, BALROG, DeepResearch Bench, PostTrainBench, TheAgentCompany, OSWorld, Vending-Bench 2, LMArena Search, Berkeley Function Calling Leaderboard (BFCL), BrowseComp-Plus
Not measured on GPQA Diamond, MMMU Pro (Vals AI), GPQA Diamond (Artificial Analysis run), Humanity's Last Exam, SimpleBench, EBR-bench, VPCT, BIG-Bench Hard, Kagi LLM Benchmark
Not measured on AIME, MATH 500 (Vals AI), MGSM (Vals AI), AA Math Index, AIME 2025 (Artificial Analysis run), MATH level 5, GSM8K
Not measured on MMLU Pro, LegalBench (Vals AI), CaseLaw (Vals AI), CorpFin (Vals AI), TaxEval (Vals AI), MortgageTax (Vals AI), MedQA (Vals AI), MMLU Pro (Artificial Analysis run), MMLU, GeoBench, AI2 Reasoning Challenge
Not measured on Vals Multimodal Index, IFBench, Fiction.LiveBench, Creative writing (Lech Mazur), CL-bench, Surface Evolver Bench, ExploitBench, HellaSwag, WinoGrande, PIQA, CL-bench Life, LMArena Vision: humor, LMArena Vision: captioning, LMArena Vision: recognizing things, LMArena Document
Not measured on Design Arena: images, Design Arena: graphic design, Design Arena: logos, LMArena Text to Image, LMArena Image Edit
Public boards shown as published (Vals AI, Artificial Analysis, Design Arena) and kept out of the coding index. Each links to its source on the benchmark page.
| Benchmark | Result | Index weight |
|---|---|---|
| Aider polyglotCoding | Not measured | Not in index |
| SWE-bench VerifiedCoding | Not measured | Not in index |
| SWE-bench LiteCoding | Not measured | Not in index |
| SWE-bench (full test set)Coding | Not measured | Not in index |
| SWE-bench MultimodalCoding | Not measured | Not in index |
| SWE-bench MultilingualCoding | Not measured | Not in index |
| LiveBench codingCoding | 84.5% | 15% |
| LMArena WebDevCoding | 1578 | 10% |
| Vals IndexGeneral | 52.3% | Not in index |
| GPQA DiamondReasoning | Not measured | Not in index |
| AIMEMath | Not measured | Not in index |
| MMLU ProKnowledge | Not measured | Not in index |
| AA Intelligence IndexIntelligence | 38.1 | Not in index |
| AA Coding IndexCoding | Not measured | Not in index |
| AA Agentic IndexAgentic work | Not measured | Not in index |
| Design Arena: websitesWeb design | 1271 | Not in index |
| Design Arena: UI componentsWeb design | 1295 | Not in index |
| Design Arena: game devWeb design | 1257 | Not in index |
| Design Arena: data vizWeb design | 1216 | Not in index |
| Design Arena: 3DWeb design | 1218 | Not in index |
| Design Arena: all code categoriesWeb design | 1270 | Not in index |
| Design Arena: SVGWeb design | 1252 | Not in index |
| Design Arena: ASCII artWeb design | 1153 | Not in index |
| Design Arena: agents building web appsAgentic work | 1191 | Not in index |
| Design Arena: agents building full-stack appsAgentic work | 1158 | Not in index |
| Design Arena: agents building mobile appsAgentic work | 1134 | Not in index |
| Design Arena: agents building Android appsAgentic work | Not measured | Not in index |
| Design Arena: agents building Godot gamesAgentic work | Not measured | Not in index |
| Design Arena: agents building gamesAgentic work | Not measured | Not in index |
| Design Arena: HTML slidesAgentic work | Not measured | Not in index |
| Design Arena: PowerPoint slidesAgentic work | Not measured | Not in index |
| Design Arena: spreadsheetsAgentic work | Not measured | Not in index |
| Design Arena: imagesImage generation | Not measured | Not in index |
| Design Arena: graphic designImage generation | Not measured | Not in index |
| Design Arena: logosImage generation | Not measured | Not in index |
| LiveBench reasoningReasoning | 81.8% | Not in index |
| LiveBench data analysisGeneral | 73.4% | Not in index |
| LiveBench researchAgentic work | 43.5% | Not in index |
| LiveBench browserAgentic work | 72.0% | Not in index |
| LiveBench long agenticAgentic work | 48.1% | Not in index |
| LiveBench designWeb design | 82.5% | Not in index |
| LiveCodeBench (Vals AI)Coding | Not measured | Not in index |
| SWE-bench Verified (Vals AI)Coding | Not measured | 15% |
| Terminal-Bench 4 (Vals AI)Coding | 13.6% | 25% |
| Vibe Code Bench (Vals AI)Coding | 81.7% | 20% |
| Code migration (Vals AI)Coding | 42.5% | Not in index |
| ProgramBench (Vals AI)Coding | 0.5% | Not in index |
| SREBench (Vals AI)Agentic work | 2.7% | Not in index |
| IOI (Vals AI)Coding | 55.6% | Not in index |
| Terminal-Bench 2.1 (Vals AI)Coding | 73.0% | Not in index |
| SWE-bench Multimodal (Vals AI)Coding | 37.5% | Not in index |
| Vibe Code Bench 1-100 (Vals AI)Coding | Not measured | Not in index |
| SkillsBench (Vals AI)Coding | Not measured | Not in index |
| CyberBench (Vals AI)Coding | 76.3% | Not in index |
| Finance Agent (Vals AI)Agentic work | 49.9% | Not in index |
| Tax Agent Bench (Vals AI)Agentic work | 19.9% | Not in index |
| Legal Research Bench (Vals AI)Agentic work | 30.3% | Not in index |
| Harvey's Legal Agent Benchmark (Vals AI)Agentic work | 4.2% | Not in index |
| Excel Modeling Benchmark (Vals AI)Agentic work | 68.5% | Not in index |
| BioMysteryBench (Vals AI)Agentic work | 61.5% | Not in index |
| Terminal-Bench-Science (Vals AI)Agentic work | 4.3% | Not in index |
| Vals Science IndexAgentic work | 28.4% | Not in index |
| Time Horizon Index (Vals AI)Agentic work | Not measured | Not in index |
| CUA-bench (Vals AI)Agentic work | Not measured | Not in index |
| Robo-bench (Vals AI)Agentic work | Not measured | Not in index |
| Public Benefits Bench (Vals AI)General | 57.6% | Not in index |
| MysteryMechanism (Vals AI)Reasoning | 19.4% | Not in index |
| MMMU Pro (Vals AI)Reasoning | Not measured | Not in index |
| MATH 500 (Vals AI)Math | Not measured | Not in index |
| MGSM (Vals AI)Math | Not measured | Not in index |
| SAGE (Vals AI)General | 48.1% | Not in index |
| LegalBench (Vals AI)Knowledge | Not measured | Not in index |
| CaseLaw (Vals AI)Knowledge | Not measured | Not in index |
| CorpFin (Vals AI)Knowledge | Not measured | Not in index |
| TaxEval (Vals AI)Knowledge | Not measured | Not in index |
| MortgageTax (Vals AI)Knowledge | Not measured | Not in index |
| MedQA (Vals AI)Knowledge | Not measured | Not in index |
| MedCode (Vals AI)Knowledge | 44.7% | Not in index |
| MedScribe (Vals AI)General | 83.7% | Not in index |
| Vals Multimodal IndexGeneral | Not measured | Not in index |
| AA Math IndexMath | Not measured | Not in index |
| GPQA Diamond (Artificial Analysis run)Reasoning | Not measured | Not in index |
| Humanity's Last Exam (Artificial Analysis run)Reasoning | 38.5% | Not in index |
| MMLU Pro (Artificial Analysis run)Knowledge | Not measured | Not in index |
| LiveCodeBench (Artificial Analysis run)Coding | Not measured | Not in index |
| SciCodeCoding | 54.6% | Not in index |
| Terminal-Bench Hard (Artificial Analysis run)Coding | Not measured | Not in index |
| IFBenchGeneral | Not measured | Not in index |
| Long context reasoning (AA-LCR)General | 83.3% | Not in index |
| τ²-Bench TelecomAgentic work | Not measured | Not in index |
| AIME 2025 (Artificial Analysis run)Math | Not measured | Not in index |
| Terminal-BenchCoding | Not measured | Not in index |
| DeepSWECoding | Not measured | Not in index |
| FrontierCodeCoding | 42.4% | 15% |
| FrontierSWECoding | Not measured | Not in index |
| GSO-BenchCoding | Not measured | Not in index |
| WeirdMLCoding | Not measured | Not in index |
| MirrorCodeCoding | Not measured | Not in index |
| APEX-AgentsAgentic work | 44.3% | Not in index |
| METR time horizonsAgentic work | Not measured | Not in index |
| Remote Labor IndexAgentic work | Not measured | Not in index |
| GDPvalAgentic work | Not measured | Not in index |
| OSWorld 2.0Agentic work | Not measured | Not in index |
| BALROGAgentic work | Not measured | Not in index |
| DeepResearch BenchAgentic work | Not measured | Not in index |
| PostTrainBenchAgentic work | Not measured | Not in index |
| GPQA Diamond (Epoch AI run)Reasoning | 90.5% | Not in index |
| ARC-AGIReasoning | 86.7% | Not in index |
| ARC-AGI-2Reasoning | 59.3% | Not in index |
| Humanity's Last ExamReasoning | Not measured | Not in index |
| SimpleBenchReasoning | Not measured | Not in index |
| Chess puzzlesReasoning | 36.0% | Not in index |
| Mystery game puzzlesReasoning | 7.0% | Not in index |
| EBR-benchReasoning | Not measured | Not in index |
| OTIS Mock AIMEMath | 98.9% | Not in index |
| FrontierMath, tiers 1 to 3Math | 78.9% | Not in index |
| FrontierMath, tier 4Math | 56.1% | Not in index |
| ProofBenchMath | 64.0% | Not in index |
| MATH level 5Math | Not measured | Not in index |
| GSM8KMath | Not measured | Not in index |
| SimpleQA VerifiedKnowledge | 41.4% | Not in index |
| MMLUKnowledge | Not measured | Not in index |
| GeoBenchKnowledge | Not measured | Not in index |
| DTBenchGeneral | 90.1% | Not in index |
| LMCAGeneral | 44.5% | Not in index |
| Fiction.LiveBenchGeneral | Not measured | Not in index |
| Creative writing (Lech Mazur)General | Not measured | Not in index |
| CL-benchGeneral | Not measured | Not in index |
| Surface Evolver BenchGeneral | Not measured | Not in index |
| Furniture assemblyGeneral | 44.2% | Not in index |
| ExploitBenchGeneral | Not measured | Not in index |
| CybenchCoding | Not measured | Not in index |
| TheAgentCompanyAgentic work | Not measured | Not in index |
| OSWorldAgentic work | Not measured | Not in index |
| SpireClimbAgentic work | 0.0% | Not in index |
| VPCTReasoning | Not measured | Not in index |
| BIG-Bench HardReasoning | Not measured | Not in index |
| AI2 Reasoning ChallengeKnowledge | Not measured | Not in index |
| HellaSwagGeneral | Not measured | Not in index |
| WinoGrandeGeneral | Not measured | Not in index |
| PIQAGeneral | Not measured | Not in index |
| CL-bench LifeGeneral | Not measured | Not in index |
| ALE-BenchCoding | 1576.9 | Not in index |
| Vending-Bench 2Agentic work | Not measured | Not in index |
| Epoch Capabilities IndexIntelligence | 156.8 | Not in index |
| LMArena TextGeneral | 1389 | Not in index |
| LMArena Text: codingCoding | 1437 | Not in index |
| LMArena Text: hard promptsReasoning | 1410 | Not in index |
| LMArena Text: mathMath | 1409 | Not in index |
| LMArena Text: instruction followingGeneral | 1408 | Not in index |
| LMArena Text: creative writingGeneral | 1363 | Not in index |
| LMArena VisionGeneral | 1216 | Not in index |
| LMArena Text: EnglishGeneral | 1393 | Not in index |
| LMArena Text: non-EnglishGeneral | 1381 | Not in index |
| LMArena Text: ChineseGeneral | 1427 | Not in index |
| LMArena Text: GermanGeneral | 1376 | Not in index |
| LMArena Text: JapaneseGeneral | 1369 | Not in index |
| LMArena Text: KoreanGeneral | 1359 | Not in index |
| LMArena Text: FrenchGeneral | 1408 | Not in index |
| LMArena Text: SpanishGeneral | 1391 | Not in index |
| LMArena Text: RussianGeneral | 1392 | Not in index |
| LMArena Text: PolishGeneral | 1383 | Not in index |
| LMArena Text: multi-turnGeneral | 1392 | Not in index |
| LMArena Text: longer queriesGeneral | 1408 | Not in index |
| LMArena Text: expertReasoning | 1442 | Not in index |
| LMArena Text: hard prompts in EnglishReasoning | 1410 | Not in index |
| LMArena Text: software and ITCoding | 1423 | Not in index |
| LMArena Text: mathematical workMath | 1427 | Not in index |
| LMArena Text: scienceKnowledge | 1386 | Not in index |
| LMArena Text: medicine and healthcareKnowledge | 1352 | Not in index |
| LMArena Text: legal and governmentKnowledge | 1400 | Not in index |
| LMArena Text: business and financeKnowledge | 1388 | Not in index |
| LMArena Text: writing and languageGeneral | 1384 | Not in index |
| LMArena Text: entertainment and mediaGeneral | 1364 | Not in index |
| LMArena WebDev: ReactCoding | 1573 | Not in index |
| LMArena WebDev: HTMLCoding | 1595 | Not in index |
| LMArena WebDev: from an imageCoding | 1571 | Not in index |
| LMArena Vision: EnglishGeneral | 1204 | Not in index |
| LMArena Vision: ChineseGeneral | 1266 | Not in index |
| LMArena Vision: reading textGeneral | 1225 | Not in index |
| LMArena Vision: diagramsReasoning | 1245 | Not in index |
| LMArena Vision: homeworkReasoning | 1261 | Not in index |
| LMArena Vision: humorGeneral | Not measured | Not in index |
| LMArena Vision: captioningGeneral | Not measured | Not in index |
| LMArena Vision: recognizing thingsGeneral | Not measured | Not in index |
| LMArena Vision: creative writingGeneral | 1205 | Not in index |
| LMArena SearchAgentic work | Not measured | Not in index |
| LMArena DocumentGeneral | Not measured | Not in index |
| LMArena Text to ImageImage generation | Not measured | Not in index |
| LMArena Image EditImage generation | Not measured | Not in index |
| Berkeley Function Calling Leaderboard (BFCL)Agentic work | Not measured | Not in index |
| Kagi LLM BenchmarkReasoning | Not measured | Not in index |
| BrowseComp-PlusAgentic work | Not measured | Not in index |
| SciCodeCoding | Not measured | Not in index |
| FACTS Benchmark SuiteKnowledge | 63.3% | Not in index |
A list price says what a token costs. The cost per solved task says what a working answer costs, which is the number that decides.
Neither board that publishes what a SWE-bench Verified attempt costs, Vals AI and swebench.com, has run this model. We leave the number out rather than estimate it.
LiveBench, on its own coding tasks, publishes what one task cost this model: $0.095, at a score of 84.5%. LiveBench counts that as $0.112 per successful task. Different tasks from SWE-bench, so it is not our number and does not enter its ranking. LiveBench coding
Beside a result, many boards publish what the run cost, how long it took, the tokens it spent or the votes behind a rating. Each figure as its board printed it, one board per row.
| Board | Result | What the run cost | Also published |
|---|---|---|---|
| LiveBench coding | 84.5% | $0.0951 per task | Output tokens per task 75,610 |
| Vals Index | 52.3% | $0.45 per test | Duration, as printed 32m 23s |
| LiveBench reasoning | 81.8% | $0.0214 per task | Output tokens per task 42,629 |
| LiveBench data analysis | 73.4% | $0.0166 per task | Output tokens per task 32,473 |
| LiveBench research | 43.5% | $0.3553 per task | Output tokens per task 241,287 |
| LiveBench browser | 72.0% | $0.2382 per task | Output tokens per task 28,295 |
| LiveBench long agentic | 48.1% | $0.9676 per task | Output tokens per task 688,782 |
| LiveBench design | 82.5% | $0.0306 per task | Output tokens per task 44,762 |
| Terminal-Bench 4 (Vals AI) | 13.6% | $0.35 per test | Duration, as printed 32m 46s |
| Vibe Code Bench (Vals AI) | 81.7% | $1.35 per test | Duration, as printed 37m 00s |
| Code migration (Vals AI) | 42.5% | $0.60 per test | Duration, as printed 50m 23s |
| ProgramBench (Vals AI) | 0.5% | $0.18 per test | Duration, as printed 28m 55s |
| SREBench (Vals AI) | 2.7% | $1.55 per test | Duration, as printed 1h 21m |
|---|---|---|---|
| IOI (Vals AI) | 55.6% | $0.20 per test | Duration, as printed 35m 47s |
| Terminal-Bench 2.1 (Vals AI) | 73.0% | $0.03 per test | Duration, as printed 7m 05s |
| SWE-bench Multimodal (Vals AI) | 37.5% | $0.03 per test | Duration, as printed 5m 16s |
| CyberBench (Vals AI) | 76.3% | $0.13 per test | Duration, as printed 15m 50s |
| Finance Agent (Vals AI) | 49.9% | $0.12 per test | Duration, as printed 14m 58s |
| Tax Agent Bench (Vals AI) | 19.9% | $0.19 per test | Duration, as printed 33m 16s |
| Legal Research Bench (Vals AI) | 30.3% | $0.44 per test | Duration, as printed 42m 28s |
| Harvey's Legal Agent Benchmark (Vals AI) | 4.2% | $0.30 per test | Duration, as printed 21m 45s |
| Excel Modeling Benchmark (Vals AI) | 68.5% | $0.14 per test | Duration, as printed 17m 21s |
| BioMysteryBench (Vals AI) | 61.5% | $0.05 per test | Duration, as printed 8m 44s |
| Terminal-Bench-Science (Vals AI) | 4.3% | $0.24 per test | Duration, as printed 1h 16m |
| Vals Science Index | 28.4% | $0.11 per test | Duration, as printed 30m 15s |
| Public Benefits Bench (Vals AI) | 57.6% | $0.22 per test | Nothing else |
| MysteryMechanism (Vals AI) | 19.4% | $0.03 per test | Duration, as printed 6m 01s |
| ProofBench | 64.0% | $0.0416 per test | Time per proof 7m 31s |
| ALE-Bench | 1576.9 | $0.018 per problem | Tokens per problem 38,984 |
| LMArena WebDev | 1578 Elo | Not published | Votes 21,622 · Interval (±) ±6.1 |
| Design Arena: websites | 1271 Elo | Not published | Battles 3,960 |
| Design Arena: UI components | 1295 Elo | Not published | Battles 1,456 |
| Design Arena: game dev | 1257 Elo | Not published | Battles 1,491 |
| Design Arena: data viz | 1216 Elo | Not published | Battles 499 |
| Design Arena: 3D | 1218 Elo | Not published | Battles 711 |
| Design Arena: all code categories | 1270 Elo | Not published | Battles 7,320 |
| Design Arena: SVG | 1252 Elo | Not published | Battles 665 |
| Design Arena: ASCII art | 1153 Elo | Not published | Battles 282 |
| Design Arena: agents building web apps | 1191 Elo | Not published | Battles 647 |
| Design Arena: agents building full-stack apps | 1158 Elo | Not published | Battles 1,053 |
| Design Arena: agents building mobile apps | 1134 Elo | Not published | Battles 234 |
| SAGE (Vals AI) | 48.1% | Not published | Latency, as printed 1m 31s |
| MedCode (Vals AI) | 44.7% | Not published | Latency, as printed 1m 49s |
| MedScribe (Vals AI) | 83.7% | Not published | Latency, as printed 2m 50s |
| APEX-Agents | 44.3% | Not published | Mean score 59.0% |
| LMArena Text | 1389 Elo | Not published | Votes 63,594 · Interval (±) ±4.4 |
| LMArena Text: coding | 1437 Elo | Not published | Votes 14,401 · Interval (±) ±6.3 |
| LMArena Text: hard prompts | 1410 Elo | Not published | Votes 39,234 · Interval (±) ±5.1 |
| LMArena Text: math | 1409 Elo | Not published | Votes 3,477 · Interval (±) ±11.0 |
| LMArena Text: instruction following | 1408 Elo | Not published | Votes 21,675 · Interval (±) ±5.8 |
| LMArena Text: creative writing | 1363 Elo | Not published | Votes 14,373 · Interval (±) ±6.7 |
| LMArena Vision | 1216 Elo | Not published | Votes 3,662 · Interval (±) ±10.8 |
| LMArena Text: English | 1393 Elo | Not published | Votes 24,531 · Interval (±) ±5.6 |
| LMArena Text: non-English | 1381 Elo | Not published | Votes 39,008 · Interval (±) ±5.1 |
| LMArena Text: Chinese | 1427 Elo | Not published | Votes 5,366 · Interval (±) ±9.3 |
| LMArena Text: German | 1376 Elo | Not published | Votes 888 · Interval (±) ±21.5 |
| LMArena Text: Japanese | 1369 Elo | Not published | Votes 1,242 · Interval (±) ±20.2 |
| LMArena Text: Korean | 1359 Elo | Not published | Votes 967 · Interval (±) ±21.1 |
| LMArena Text: French | 1408 Elo | Not published | Votes 2,755 · Interval (±) ±13.9 |
| LMArena Text: Spanish | 1391 Elo | Not published | Votes 2,391 · Interval (±) ±13.7 |
| LMArena Text: Russian | 1392 Elo | Not published | Votes 8,535 · Interval (±) ±7.5 |
| LMArena Text: Polish | 1383 Elo | Not published | Votes 883 · Interval (±) ±20.7 |
| LMArena Text: multi-turn | 1392 Elo | Not published | Votes 9,135 · Interval (±) ±7.4 |
| LMArena Text: longer queries | 1408 Elo | Not published | Votes 27,335 · Interval (±) ±5.7 |
| LMArena Text: expert | 1442 Elo | Not published | Votes 6,698 · Interval (±) ±8.2 |
| LMArena Text: hard prompts in English | 1410 Elo | Not published | Votes 15,274 · Interval (±) ±6.2 |
| LMArena Text: software and IT | 1423 Elo | Not published | Votes 22,318 · Interval (±) ±5.7 |
| LMArena Text: mathematical work | 1427 Elo | Not published | Votes 3,897 · Interval (±) ±10.6 |
| LMArena Text: science | 1386 Elo | Not published | Votes 10,709 · Interval (±) ±7.0 |
| LMArena Text: medicine and healthcare | 1352 Elo | Not published | Votes 4,547 · Interval (±) ±10.1 |
| LMArena Text: legal and government | 1400 Elo | Not published | Votes 5,212 · Interval (±) ±9.3 |
| LMArena Text: business and finance | 1388 Elo | Not published | Votes 10,905 · Interval (±) ±6.8 |
| LMArena Text: writing and language | 1384 Elo | Not published | Votes 18,351 · Interval (±) ±6.1 |
| LMArena Text: entertainment and media | 1364 Elo | Not published | Votes 16,757 · Interval (±) ±6.3 |
| LMArena WebDev: React | 1573 Elo | Not published | Votes 13,375 · Interval (±) ±7.0 |
| LMArena WebDev: HTML | 1595 Elo | Not published | Votes 3,220 · Interval (±) ±12.3 |
| LMArena WebDev: from an image | 1571 Elo | Not published | Votes 4,439 · Interval (±) ±9.9 |
| LMArena Vision: English | 1204 Elo | Not published | Votes 1,264 · Interval (±) ±18.1 |
| LMArena Vision: Chinese | 1266 Elo | Not published | Votes 169 · Interval (±) ±43.9 |
| LMArena Vision: reading text | 1225 Elo | Not published | Votes 2,489 · Interval (±) ±12.4 |
| LMArena Vision: diagrams | 1245 Elo | Not published | Votes 905 · Interval (±) ±20.4 |
| LMArena Vision: homework | 1261 Elo | Not published | Votes 550 · Interval (±) ±25.3 |
| LMArena Vision: creative writing | 1205 Elo | Not published | Votes 327 · Interval (±) ±34.3 |