Claude Fable 5.1: benchmark results
Anthropic's Claude Fable 5.1 (September 1, 2026), its flagship model for coding, research and enterprise work, built for multi-day autonomous agentic sessions. Provider: Anthropic. Released 2026-09-01. Access: API.
Aggregate Rating 1958 ± 5, rank #9 of 1656 rated models, from 631 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| A2Z GameSpec-Bench - Adaptive Playtest Big | 74.7 | Adaptive Playtest Big (%; coding-agent game design fidelity; | 100 |
| A2Z GameSpec-Bench - Adaptive Playtest Small | 85.2 | Adaptive Playtest Small (%; coding-agent game design fidelit | 100 |
| A2Z GameSpec-Bench - GDD Fidelity | 77 | GDD Fidelity (%; coding-agent game design fidelity; Table 2) | 100 |
| A2Z GameSpec-Bench - GDD Fidelity Big | 71.1 | GDD Fidelity Big (%; coding-agent game design fidelity; Tabl | 100 |
| A2Z GameSpec-Bench - GDD Fidelity Small | 82.8 | GDD Fidelity Small (%; coding-agent game design fidelity; Ta | 100 |
| A2Z GameSpec-Bench - Scenario Replay Big | 55.1 | Scenario Replay Big (%; coding-agent game design fidelity; T | 100 |
| A2Z GameSpec-Bench - Scenario Replay Small | 73.5 | Scenario Replay Small (%; coding-agent game design fidelity; | 100 |
| A2Z GameSpec-Bench - Source Code Big | 83.5 | Source Code Big (%; coding-agent game design fidelity; Table | 100 |
| A2Z GameSpec-Bench - Source Code Small | 89.7 | Source Code Small (%; coding-agent game design fidelity; Tab | 100 |
| AA GDP.pdf - Insurance - Criterion Pass Rate | 89.15 | Criterion Pass Rate (%) | 100 |
| AA GDP.pdf - Manufacturing/Supply Chains - Criterion Pass Rate | 82.56 | Criterion Pass Rate (%) | 100 |
| AA Terminal-Bench 2.1 | 91.39 | Pass@1 (%) | 100 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1 · How It Works · Data refreshed daily, snapshot 2026-10-20.