# Google Gemini 3.5 Flash As of October 22, 2026, Google Gemini 3.5 Flash ranks #31 of 124 models overall with 63.8 ±11.7 on the LLMBenchmark Index. Gemini 3.5 Flash ranks #11 of 75 in knowledge, its strongest category. Google Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens. Gemini 3.5 Flash was released on May 19, 2026. Page: https://llmbenchmark.ai/models/gemini-3-5-flash Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: Google - Released: May 19, 2026 - Price per million input tokens: $1.50 - Price per million output tokens: $9.00 - Context window: 1.05M tokens - Overall rank: 31 of 124, by the LLMBenchmark Index - LLMBenchmark Index: 63.8 ±11.7 (90% margin, from 6 of 7 inputs) - Artificial Analysis Intelligence Index: 33.6 - Vibe Coding Index: 39.8 (from 4 of 6 coding benchmarks) Benchmark results (112 of 195): - LMArena WebDev: 1499 Elo (source: LMArena WebDev, read October 22, 2026) - GPQA Diamond: 92.7% (source: GPQA (Vals AI), read October 22, 2026) - MMLU Pro: 89.5% (source: MMLU Pro (Vals AI), read October 22, 2026) - AA Intelligence Index: 33.6 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 1267 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 1270 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1263 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1237 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 1243 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1266 Elo (source: Design Arena, read October 22, 2026) - Design Arena: SVG: 1253 Elo (source: Design Arena, read October 22, 2026) - Design Arena: ASCII art: 1254 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building web apps: 1202 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building full-stack apps: 1197 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building mobile apps: 1174 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building Android apps: 1185 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building Godot games: 1098 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building games: 1180 Elo (source: Design Arena, read October 22, 2026) - Design Arena: HTML slides: 1093 Elo (source: Design Arena, read October 22, 2026) - Design Arena: PowerPoint slides: 1156 Elo (source: Design Arena, read October 22, 2026) - LiveCodeBench (Vals AI): 87.6% (source: Vals AI boards, read October 22, 2026) - SWE-bench Verified (Vals AI): 78.8% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench 4 (Vals AI): 6.1% (source: Vals AI boards, read October 22, 2026) - Vibe Code Bench (Vals AI): 48.7% (source: Vals AI boards, read October 22, 2026) - Code migration (Vals AI): 26.8% (source: Vals AI boards, read October 22, 2026) - ProgramBench (Vals AI): 0.0% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench 2.1 (Vals AI): 74.2% (source: Vals AI boards, read October 22, 2026) - SkillsBench (Vals AI): 52.7% (source: Vals AI boards, read October 22, 2026) - Finance Agent (Vals AI): 57.9% (source: Vals AI boards, read October 22, 2026) - Tax Agent Bench (Vals AI): 21.6% (source: Vals AI boards, read October 22, 2026) - Legal Research Bench (Vals AI): 30.8% (source: Vals AI boards, read October 22, 2026) - Excel Modeling Benchmark (Vals AI): 63.5% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench-Science (Vals AI): 5.7% (source: Vals AI boards, read October 22, 2026) - Public Benefits Bench (Vals AI): 59.5% (source: Vals AI boards, read October 22, 2026) - MMMU Pro (Vals AI): 88.3% (source: Vals AI boards, read October 22, 2026) - SAGE (Vals AI): 49.9% (source: Vals AI boards, read October 22, 2026) - LegalBench (Vals AI): 83.6% (source: Vals AI boards, read October 22, 2026) - CorpFin (Vals AI): 64.7% (source: Vals AI boards, read October 22, 2026) - TaxEval (Vals AI): 74.4% (source: Vals AI boards, read October 22, 2026) - MortgageTax (Vals AI): 68.1% (source: Vals AI boards, read October 22, 2026) - MedCode (Vals AI): 55.8% (source: Vals AI boards, read October 22, 2026) - MedScribe (Vals AI): 76.6% (source: Vals AI boards, read October 22, 2026) - Vals Multimodal Index: 62.9% (source: Vals AI boards, read October 22, 2026) - GPQA Diamond (Artificial Analysis run): 92.2% (source: Artificial Analysis, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 42.7% (source: Artificial Analysis, read October 22, 2026) - SciCode: 53.9% (source: Artificial Analysis, read October 22, 2026) - Terminal-Bench Hard (Artificial Analysis run): 46.2% (source: Artificial Analysis, read October 22, 2026) - IFBench: 76.3% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 74.3% (source: Artificial Analysis, read October 22, 2026) - τ²-Bench Telecom: 95.6% (source: Artificial Analysis, read October 22, 2026) - WeirdML: 62.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - APEX-Agents: 27.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - GPQA Diamond (Epoch AI run): 92.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 92.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 72.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleBench: 76.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - Chess puzzles: 45.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Mystery game puzzles: 32.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - EBR-bench: 4.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 95.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tiers 1 to 3: 62.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tier 4: 26.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - ProofBench: 31.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleQA Verified: 66.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 94.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 47.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - Surface Evolver Bench: 58.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - ALE-Bench: 911.0 (source: ALE-Bench (Sakana AI), read October 22, 2026) - Vending-Bench 2: $5,396 (source: Epoch AI benchmarking hub, read October 22, 2026) - Epoch Capabilities Index: 154.9 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1482 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1493 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1488 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1504 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1467 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1470 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1308 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1481 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1475 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1527 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1494 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1486 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1448 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1490 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1480 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1493 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1516 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1481 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1483 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1495 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1483 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1494 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1495 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1495 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1483 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1488 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1467 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1478 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1459 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: React: 1495 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: HTML: 1522 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: from an image: 1504 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1305 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1377 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1317 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1323 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1330 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: humor: 1321 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: creative writing: 1301 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Document: 1463 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - SciCode: 12.3% (source: Kaggle Benchmarks, read October 22, 2026) - FACTS Benchmark Suite: 63.1% (source: Kaggle Benchmarks, read October 22, 2026)