Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback): benchmark results
Provider: Anthropic. Released 2026-09-01. Access: API.
Unified ELO 1747 ± 1, rank #34 of 1761 rated models, from 19 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Humanity's Last Exam | 55.93 | Accuracy (%) | 99.7 |
| AA Omniscience - Business | 55.8 | Accuracy (%) | 99.4 |
| AA Omniscience - Health | 55.5 | Accuracy (%) | 99.4 |
| AA Omniscience - Humanities & Social Sciences | 63.1 | Accuracy (%) | 99.4 |
| AA Omniscience - Law | 66.1 | Accuracy (%) | 99.4 |
| AA Omniscience - Science, Engineering & Mathematics | 60 | Accuracy (%) | 99.4 |
| AA-Omniscience Accuracy | 64.93 | Accuracy (%) | 99.4 |
| AA CritPt | 30.29 | Accuracy (%) | 99 |
| AA Omniscience | 40.8 | Score | 98.6 |
| AA Omniscience - Software Engineering (SWE) | 89.1 | Accuracy (%) | 98.5 |
| AA Long Context Reasoning | 83.67 | Accuracy (%) | 98.3 |
| Artificial Analysis Intelligence Index | 51.67 | Intelligence Index | 98.2 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1-adaptive-reasoning-high-effort-default-fallback · How It Works · Data refreshed daily, snapshot 2026-09-05.