Claude Fable 5.1
Claude Fable 5.1 improves on Fable 5 across agentic coding, long-running workflows, front-end and visual code generation, finance, analysis, and knowledge work, with more concise plans and summaries. Anthropic retains prompts and outputs for 30 days; Zero Data Retention is not available.
- Reasoning
- Vision
- Native PDF input
- Tool Calling
- Structured Output
Added Sep 1, 2026
Pricing
Auto routing · per 1M tokens- Input
- $10.00
- Output
- $50.00
- Cache read
- $0.25
Specifications
- Context window
- 1M
- Max output
- 128K
- Avg output (7d)
- 2.3K tokens
- Longer than 95% of models
Benchmarks
Benchmarks
Sourced from Artificial Analysis.
Intelligence Index
53.4
Coding Index
81.6
Agentic Index
57.9
Agentic work
AutomationBench-AA
Workflow automation with guardrail penalties
59.4%
Better than 83% of models compared
AutomationBench-AA Tasks Completed
Fully completed workflows without guardrail violations
32.1%
Better than 55% of models compared
Harvey LAB-AA
Legal agentic work criterion pass rate
93.0%
Better than 84% of models compared
AA-Briefcase
Agentic knowledge work (Elo)
1675 Elo
Better than 97% of models compared
GDPval-AA v2
Economically valuable tasks (Elo)
1758 Elo
Better than 99% of models compared
Document reasoning
GDP.pdf
Professional PDF reasoning: all-pass rate
26.2%
Better than 90% of models compared
AA-LCR v1.1
Long context reasoning with updated grading
85.3%
Better than 99% of models compared
MLCR-AA
Medical long-context reasoning
71.1%
Better than 98% of models compared
Reasoning
HLE
Humanity's Last Exam
59.1%
Better than 99% of models compared
CritPt
Research-level physics reasoning
29.7%
Coding
Terminal-Bench v4.0
Practical coding and terminal tasks
52.0%
Better than 93% of models compared
SciCode
Python programming for scientific computing
63.1%
Better than 99% of models compared
Knowledge
AA-Omniscience Accuracy
Proportion of correctly answered questions
67.2%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
72.6%
Legacy benchmarks
GPQA Diamond (legacy)
Graduate-level scientific reasoning
93.7%
Better than 98% of models compared
AA-LCR (unversioned / legacy)
Long context reasoning evaluation
85.3%
Better than 99% of models compared
GDPval-AA (unversioned / legacy)
Economically valuable tasks
62.7%
Last updated Oct 14, 2026
Artificial AnalysisProviders
Auto routing is available for this model. Explicit provider selection is not available.
Loading provider options…