Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
Anthropic · Active

Claude Fable 5

claude-fable family · launched 2026-06-09

MultimodalReasoningToolsStructured
AITopic score68.8#31 overall

Claude model for creative writing, analysis, and controlled agent workflows

Evidence coverage100%9 evaluations · 3 institutions
Context / maximum output1M / 128ktokens
Cache / input / output$1 · $10 · $50USD per million tokens
Value / freshness44.7 / 70relative value · release freshness
Product profile

What this model supports

Inputtext, image, pdf
Outputtext
Knowledge cutoff2026-01-31
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding68.02 public results
Research & reasoning69.52 public results
Professional work68.82 public results
Knowledge & instruction69.92 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Coding2 results

LiveBench 2.0 · CodingLiveBench98.30 scoreReading 98.3

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · CodingAIHOT68.00 scoreReading 68.0

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Research & reasoning2 results

LiveBench 2.0 · ResearchLiveBench89.70 scoreReading 89.7

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · ResearchAIHOT69.50 scoreReading 69.5

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Professional work2 results

LiveBench 2.0 · ProfessionalLiveBench77.60 scoreReading 77.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · ProfessionalAIHOT68.80 scoreReading 68.8

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Knowledge & instruction2 results

LiveBench 2.0 · KnowledgeLiveBench86.90 scoreReading 86.9

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · KnowledgeAIHOT69.90 scoreReading 69.9

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence

Human preference & indices4 results

LiveBenchLiveBench83.61 scoreReading 83.6

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AA IndexArtificial Analysis68.86 indexReading 70.0

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence
Arena TextLMArena1,491.6 EloReading 68.8

Direct LMArena text leaderboard result.

Open evidence
AIHOT aggregate leaderboardAIHOT68.80 scoreReading 68.8

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: AIHOT aggregateOpen evidence
Same builder

More from Anthropic