# Google Gemini 3.7 Flash As of October 22, 2026, Google Gemini 3.7 Flash ranks #30 of 124 models overall with 65.7 ±11.5 on the LLMBenchmark Index. Gemini 3.7 Flash ranks #13 of 123 in reasoning, its strongest category. Google Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens. Gemini 3.7 Flash was released on August 13, 2026. Page: https://llmbenchmark.ai/models/gemini-3-7-flash Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: Google - Released: August 13, 2026 - Price per million input tokens: $0.75 - Price per million output tokens: $3.75 - Context window: 1.05M tokens - Overall rank: 30 of 124, by the LLMBenchmark Index - LLMBenchmark Index: 65.7 ±11.5 (90% margin, from 7 of 7 inputs) - Artificial Analysis Intelligence Index: 39.6 - Vibe Coding Index: 58.0 (from 6 of 6 coding benchmarks) Benchmark results (114 of 195): - LiveBench coding: 80.5% (source: LiveBench, read October 22, 2026) - LMArena WebDev: 1591 Elo (source: LMArena WebDev, read October 22, 2026) - GPQA Diamond: 93.9% (source: GPQA (Vals AI), read October 22, 2026) - MMLU Pro: 90.1% (source: MMLU Pro (Vals AI), read October 22, 2026) - AA Intelligence Index: 39.6 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - AA Coding Index: 71.5 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 1303 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 1295 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1318 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1315 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 1307 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1307 Elo (source: Design Arena, read October 22, 2026) - Design Arena: SVG: 1283 Elo (source: Design Arena, read October 22, 2026) - Design Arena: ASCII art: 1278 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building web apps: 1223 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building full-stack apps: 1208 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building mobile apps: 1230 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building Android apps: 1243 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building Godot games: 1264 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building games: 1235 Elo (source: Design Arena, read October 22, 2026) - Design Arena: spreadsheets: 1091 Elo (source: Design Arena, read October 22, 2026) - LiveBench reasoning: 87.8% (source: LiveBench, read October 22, 2026) - LiveBench data analysis: 68.0% (source: LiveBench, read October 22, 2026) - LiveBench research: 76.5% (source: LiveBench, read October 22, 2026) - LiveBench browser: 56.0% (source: LiveBench, read October 22, 2026) - LiveBench long agentic: 28.3% (source: LiveBench, read October 22, 2026) - LiveBench design: 73.2% (source: LiveBench, read October 22, 2026) - LiveCodeBench (Vals AI): 88.7% (source: Vals AI boards, read October 22, 2026) - SWE-bench Verified (Vals AI): 80.8% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench 4 (Vals AI): 12.1% (source: Vals AI boards, read October 22, 2026) - Vibe Code Bench (Vals AI): 70.4% (source: Vals AI boards, read October 22, 2026) - Code migration (Vals AI): 34.8% (source: Vals AI boards, read October 22, 2026) - ProgramBench (Vals AI): 0.0% (source: Vals AI boards, read October 22, 2026) - SREBench (Vals AI): 4.6% (source: Vals AI boards, read October 22, 2026) - IOI (Vals AI): 67.8% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench 2.1 (Vals AI): 77.5% (source: Vals AI boards, read October 22, 2026) - SkillsBench (Vals AI): 65.9% (source: Vals AI boards, read October 22, 2026) - CyberBench (Vals AI): 43.8% (source: Vals AI boards, read October 22, 2026) - Finance Agent (Vals AI): 59.0% (source: Vals AI boards, read October 22, 2026) - Tax Agent Bench (Vals AI): 22.8% (source: Vals AI boards, read October 22, 2026) - Legal Research Bench (Vals AI): 34.6% (source: Vals AI boards, read October 22, 2026) - Excel Modeling Benchmark (Vals AI): 71.3% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench-Science (Vals AI): 7.1% (source: Vals AI boards, read October 22, 2026) - MMMU Pro (Vals AI): 89.0% (source: Vals AI boards, read October 22, 2026) - SAGE (Vals AI): 49.2% (source: Vals AI boards, read October 22, 2026) - LegalBench (Vals AI): 87.3% (source: Vals AI boards, read October 22, 2026) - TaxEval (Vals AI): 74.7% (source: Vals AI boards, read October 22, 2026) - MortgageTax (Vals AI): 66.7% (source: Vals AI boards, read October 22, 2026) - MedCode (Vals AI): 53.4% (source: Vals AI boards, read October 22, 2026) - MedScribe (Vals AI): 83.9% (source: Vals AI boards, read October 22, 2026) - GPQA Diamond (Artificial Analysis run): 94.5% (source: Artificial Analysis, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 47.9% (source: Artificial Analysis, read October 22, 2026) - SciCode: 59.8% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 83.0% (source: Artificial Analysis, read October 22, 2026) - FrontierCode: 43.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierSWE: 20.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - APEX-Agents: 67.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - Remote Labor Index: 5.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - GPQA Diamond (Epoch AI run): 94.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 95.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 84.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - Chess puzzles: 66.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Mystery game puzzles: 37.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 97.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tiers 1 to 3: 71.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tier 4: 36.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - ProofBench: 58.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleQA Verified: 69.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 96.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 50.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - Furniture assembly: 26.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - ALE-Bench: 904.3 (source: ALE-Bench (Sakana AI), read October 22, 2026) - Epoch Capabilities Index: 158.0 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1489 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1499 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1495 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1511 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1484 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1488 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1314 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1483 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1487 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1552 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1506 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1511 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1481 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1500 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1495 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1515 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1503 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1485 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1492 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1512 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1487 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1498 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1502 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1511 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1494 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1496 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1479 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1491 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1477 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: React: 1587 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: HTML: 1593 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: from an image: 1599 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1309 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1394 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1322 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1329 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1320 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: humor: 1299 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: creative writing: 1312 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - SciCode: 13.8% (source: Kaggle Benchmarks, read October 22, 2026) - FACTS Benchmark Suite: 71.2% (source: Kaggle Benchmarks, read October 22, 2026)