# Anthropic Claude Fable 5.1 As of October 22, 2026, Anthropic Claude Fable 5.1 ranks #2 of 123 models overall with 84.7 ±2.9 on the LLMBenchmark Index. Claude Fable 5.1 ranks #1 of 108 in math, its strongest category. Anthropic Claude Fable 5.1 costs $10.00 per million input tokens and $50.00 per million output tokens. Claude Fable 5.1 was released on September 1, 2026. Page: https://llmbenchmark.ai/models/claude-fable-5-1 Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: Anthropic - Released: September 1, 2026 - Price per million input tokens: $10.00 - Price per million output tokens: $50.00 - Context window: 1M tokens - Overall rank: 2 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 84.7 ±2.9 (90% margin, from 7 of 7 inputs) - Artificial Analysis Intelligence Index: 53.4 - Vibe Coding Index: 84.2 (from 5 of 6 coding benchmarks) Benchmark results (124 of 195): - LiveBench coding: 97.7% (source: LiveBench, read October 22, 2026) - LMArena WebDev: 1743 Elo (source: LMArena WebDev, read October 22, 2026) - GPQA Diamond: 93.4% (source: GPQA (Vals AI), read October 22, 2026) - MMLU Pro: 92.4% (source: MMLU Pro (Vals AI), read October 22, 2026) - AA Intelligence Index: 53.4 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - AA Coding Index: 81.6 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - AA Agentic Index: 57.9 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 1312 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 1336 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1381 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1344 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 1392 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1335 Elo (source: Design Arena, read October 22, 2026) - Design Arena: SVG: 1300 Elo (source: Design Arena, read October 22, 2026) - Design Arena: ASCII art: 1323 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building web apps: 1318 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building full-stack apps: 1326 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building mobile apps: 1267 Elo (source: Design Arena, read October 22, 2026) - Design Arena: agents building Godot games: 1327 Elo (source: Design Arena, read October 22, 2026) - Design Arena: PowerPoint slides: 1305 Elo (source: Design Arena, read October 22, 2026) - Design Arena: spreadsheets: 1380 Elo (source: Design Arena, read October 22, 2026) - LiveBench reasoning: 91.7% (source: LiveBench, read October 22, 2026) - LiveBench data analysis: 80.3% (source: LiveBench, read October 22, 2026) - LiveBench research: 82.0% (source: LiveBench, read October 22, 2026) - LiveBench browser: 100.0% (source: LiveBench, read October 22, 2026) - LiveBench long agentic: 80.8% (source: LiveBench, read October 22, 2026) - LiveBench design: 83.4% (source: LiveBench, read October 22, 2026) - LiveCodeBench (Vals AI): 90.5% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench 4 (Vals AI): 58.1% (source: Vals AI boards, read October 22, 2026) - Vibe Code Bench (Vals AI): 90.3% (source: Vals AI boards, read October 22, 2026) - Code migration (Vals AI): 54.6% (source: Vals AI boards, read October 22, 2026) - ProgramBench (Vals AI): 7.0% (source: Vals AI boards, read October 22, 2026) - SREBench (Vals AI): 22.9% (source: Vals AI boards, read October 22, 2026) - IOI (Vals AI): 90.8% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench 2.1 (Vals AI): 85.0% (source: Vals AI boards, read October 22, 2026) - SWE-bench Multimodal (Vals AI): 61.3% (source: Vals AI boards, read October 22, 2026) - Vibe Code Bench 1-100 (Vals AI): 28.0% (source: Vals AI boards, read October 22, 2026) - SkillsBench (Vals AI): 61.5% (source: Vals AI boards, read October 22, 2026) - CyberBench (Vals AI): 70.4% (source: Vals AI boards, read October 22, 2026) - Finance Agent (Vals AI): 58.9% (source: Vals AI boards, read October 22, 2026) - Tax Agent Bench (Vals AI): 49.2% (source: Vals AI boards, read October 22, 2026) - Legal Research Bench (Vals AI): 55.3% (source: Vals AI boards, read October 22, 2026) - Excel Modeling Benchmark (Vals AI): 76.7% (source: Vals AI boards, read October 22, 2026) - Terminal-Bench-Science (Vals AI): 40.0% (source: Vals AI boards, read October 22, 2026) - Time Horizon Index (Vals AI): 63.3% (source: Vals AI boards, read October 22, 2026) - CUA-bench (Vals AI): 13.2% (source: Vals AI boards, read October 22, 2026) - Robo-bench (Vals AI): 5.8% (source: Vals AI boards, read October 22, 2026) - Public Benefits Bench (Vals AI): 74.9% (source: Vals AI boards, read October 22, 2026) - MysteryMechanism (Vals AI): 47.8% (source: Vals AI boards, read October 22, 2026) - MMMU Pro (Vals AI): 90.6% (source: Vals AI boards, read October 22, 2026) - SAGE (Vals AI): 48.5% (source: Vals AI boards, read October 22, 2026) - LegalBench (Vals AI): 88.5% (source: Vals AI boards, read October 22, 2026) - TaxEval (Vals AI): 76.0% (source: Vals AI boards, read October 22, 2026) - MortgageTax (Vals AI): 70.8% (source: Vals AI boards, read October 22, 2026) - MedCode (Vals AI): 53.5% (source: Vals AI boards, read October 22, 2026) - MedScribe (Vals AI): 91.3% (source: Vals AI boards, read October 22, 2026) - GPQA Diamond (Artificial Analysis run): 93.7% (source: Artificial Analysis, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 59.1% (source: Artificial Analysis, read October 22, 2026) - SciCode: 63.1% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 85.3% (source: Artificial Analysis, read October 22, 2026) - FrontierCode: 50.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierSWE: 56.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - GSO-Bench: 88.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - WeirdML: 92.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - MirrorCode: 73.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - APEX-Agents: 68.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - Remote Labor Index: 17.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 97.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 90.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Chess puzzles: 48.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Mystery game puzzles: 58.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - EBR-bench: 57.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 100.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tiers 1 to 3: 90.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tier 4: 87.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - ProofBench: 100.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleQA Verified: 70.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 97.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 65.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - Furniture assembly: 70.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - SpireClimb: 2.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - ALE-Bench: 2143.2 (source: ALE-Bench (Sakana AI), read October 22, 2026) - Vending-Bench 2: $5,422 (source: Epoch AI benchmarking hub, read October 22, 2026) - Epoch Capabilities Index: 166.5 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1512 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1532 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1528 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1531 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1518 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1509 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1319 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1506 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1508 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1584 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1499 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1562 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1517 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1523 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1520 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1520 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1525 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1493 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1524 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1544 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1522 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1530 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1541 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1532 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1531 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1514 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1493 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1510 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1497 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: React: 1792 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: HTML: 1684 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: from an image: 1722 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1313 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1391 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1327 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1343 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1345 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: humor: 1318 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: creative writing: 1330 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Search: 1246 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)