# Anthropic Claude Sonnet 4.6 As of October 21, 2026, Anthropic Claude Sonnet 4.6 ranks #44 of 123 models overall with 60.3 ±8.7 on the LLMBenchmark Index. Claude Sonnet 4.6 ranks #26 of 133 in web design, its strongest category. Anthropic Claude Sonnet 4.6 costs $3.00 per million input tokens and $15.00 per million output tokens. Claude Sonnet 4.6 was released on February 17, 2026. Page: https://llmbenchmark.ai/models/claude-sonnet-4-6 Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: Anthropic - Released: February 17, 2026 - Price per million input tokens: $3.00 - Price per million output tokens: $15.00 - Context window: 1M tokens - Overall rank: 44 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 60.3 ±8.7 (90% margin, from 7 of 7 inputs) - Artificial Analysis Intelligence Index: 30.1 - Vibe Coding Index: 57.3 (from 5 of 6 coding benchmarks) Benchmark results (118 of 195): - LiveBench coding: 66.6% (source: LiveBench, read October 21, 2026) - LMArena WebDev: 1523 Elo (source: LMArena WebDev, read October 21, 2026) - GPQA Diamond: 85.6% (source: GPQA (Vals AI), read October 21, 2026) - AIME: 92.3% (source: AIME (Vals AI), read October 21, 2026) - MMLU Pro: 87.3% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 30.1 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Coding Index: 63.0 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - AA Agentic Index: 31.8 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1285 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1272 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1259 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1277 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 1234 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1276 Elo (source: Design Arena, read October 21, 2026) - Design Arena: SVG: 1197 Elo (source: Design Arena, read October 21, 2026) - Design Arena: ASCII art: 1235 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building web apps: 1190 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building full-stack apps: 1213 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building mobile apps: 1212 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building Android apps: 1196 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building Godot games: 1226 Elo (source: Design Arena, read October 21, 2026) - Design Arena: agents building games: 1177 Elo (source: Design Arena, read October 21, 2026) - LiveBench reasoning: 86.4% (source: LiveBench, read October 21, 2026) - LiveBench data analysis: 76.1% (source: LiveBench, read October 21, 2026) - LiveBench research: 63.6% (source: LiveBench, read October 21, 2026) - LiveBench browser: 68.0% (source: LiveBench, read October 21, 2026) - LiveBench long agentic: 23.1% (source: LiveBench, read October 21, 2026) - LiveBench design: 71.8% (source: LiveBench, read October 21, 2026) - LiveCodeBench (Vals AI): 82.1% (source: Vals AI boards, read October 21, 2026) - SWE-bench Verified (Vals AI): 77.4% (source: Vals AI boards, read October 21, 2026) - Vibe Code Bench (Vals AI): 55.8% (source: Vals AI boards, read October 21, 2026) - Code migration (Vals AI): 39.9% (source: Vals AI boards, read October 21, 2026) - ProgramBench (Vals AI): 0.5% (source: Vals AI boards, read October 21, 2026) - Terminal-Bench 2.1 (Vals AI): 57.3% (source: Vals AI boards, read October 21, 2026) - SkillsBench (Vals AI): 49.0% (source: Vals AI boards, read October 21, 2026) - Finance Agent (Vals AI): 51.0% (source: Vals AI boards, read October 21, 2026) - Tax Agent Bench (Vals AI): 25.8% (source: Vals AI boards, read October 21, 2026) - Legal Research Bench (Vals AI): 38.5% (source: Vals AI boards, read October 21, 2026) - Excel Modeling Benchmark (Vals AI): 60.2% (source: Vals AI boards, read October 21, 2026) - Public Benefits Bench (Vals AI): 62.5% (source: Vals AI boards, read October 21, 2026) - MMMU Pro (Vals AI): 83.6% (source: Vals AI boards, read October 21, 2026) - SAGE (Vals AI): 46.6% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 82.1% (source: Vals AI boards, read October 21, 2026) - CaseLaw (Vals AI): 64.0% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 65.3% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 77.1% (source: Vals AI boards, read October 21, 2026) - MortgageTax (Vals AI): 67.7% (source: Vals AI boards, read October 21, 2026) - MedQA (Vals AI): 92.1% (source: Vals AI boards, read October 21, 2026) - Vals Multimodal Index: 60.6% (source: Vals AI boards, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 87.5% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 33.6% (source: Artificial Analysis, read October 21, 2026) - SciCode: 50.1% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench Hard (Artificial Analysis run): 53.0% (source: Artificial Analysis, read October 21, 2026) - IFBench: 56.6% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 80.0% (source: Artificial Analysis, read October 21, 2026) - τ²-Bench Telecom: 79.5% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench: 53.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierCode: 24.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - WeirdML: 66.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - APEX-Agents: 43.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OSWorld 2.0: 9.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - DeepResearch Bench: 54.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 87.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI: 86.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI-2: 60.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 23.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 16.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 85.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - ProofBench: 45.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleQA Verified: 35.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 89.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 46.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ExploitBench: 23.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - OSWorld: 72.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - Vending-Bench 2: $7,204 (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 152.8 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1458 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1503 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1485 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1462 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1476 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1435 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: 1283 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1472 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1440 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1491 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1428 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1420 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1410 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1465 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1464 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1440 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1443 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1464 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1479 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1500 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1493 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1491 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1483 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1474 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1451 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1470 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1464 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1444 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1431 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: React: 1512 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: HTML: 1527 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena WebDev: from an image: 1529 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: English: 1298 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: Chinese: 1307 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: reading text: 1296 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: diagrams: 1306 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: homework: 1311 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: humor: 1248 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: recognizing things: 1195 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: creative writing: 1272 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Document: 1482 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - FACTS Benchmark Suite: 37.0% (source: Kaggle Benchmarks, read October 21, 2026)