Anthropic
Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)
Claude Fable 5.1 improves on Fable 5 across long-running agentic coding, knowledge work, and research, following instructions precisely over sessions that run unattended for hours.
Claude release notesModel Snapshot
TypeLanguage
ReleaseAug 31, 2026
Context1,000,000
Tagsreasoning, tool-use, explicit-caching, file-input
Overall
Rank #10 across 687
51.2
Coding
Rank #3 across 330
79.1
Blended Price
Rank #412 across 432
$20.00/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed48.8 tok/s
First Token7.10s
Max Output128,000
Pricing
Blended$20.00/M
Input$10.00/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 51.2 | #10 |
| Artificial Analysis Coding Index | coding | 79.1 | #3 |
| GPQA | reasoning | 90.6% | #60 |
| Humanity's Last Exam | reasoning | 55.9% | #5 |
| SciCode |