Anthropic
Anthropic: Claude Fable 5.1 (batch)
anthropic/claude-fable-5.1:batch
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual code generation, and finance and analysis tasks in particular. It also tends to be more concise than Fable 5 in its plans and summaries. We recommend testing it as a direct upgrade wherever you use Fable 5 today, and alongside Opus 5 on reasoning-heavy tasks.
/ 1M tokens
/ 1M tokens
tokens
Limits
Context
1,000,000
tokens
Max output
128,000
13% of the context window
Model facts
Author
Anthropic
Tokenizer
Claude
Modality
Text + Image + File -> Text
Created
Sep 1, 2026
Reasoning
Publication status
Modalities
Generation controls
Capability scores
Better than 98% of models compared
Better than 98% of models compared
Better than 97% of models compared
Agent tasks
Category performance
1328 Elo
62.6% win
1327 Elo
60.7% win
1326 Elo
57.2% win
1265 Elo
56.3% win
1309 Elo
56.1% win
Creative tasks
Category performance
1393 Elo
67.7% win
1384 Elo
65.6% win
1325 Elo
65.0% win
1344 Elo
61.8% win
1338 Elo
59.6% win
1338 Elo
59.3% win
1301 Elo
56.4% win
1314 Elo
56.3% win