Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback): benchmark results
Provider: Anthropic. Released 2026-09-01. Access: API.
Unified ELO 1778 ± 1, rank #14 of 1761 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Law | 68.6 | Accuracy (%) | 100 |
| AA Humanity's Last Exam | 58.71 | Accuracy (%) | 99.8 |
| AA Omniscience - Science, Engineering & Mathematics | 61.7 | Accuracy (%) | 99.8 |
| AA-Omniscience Accuracy | 66.22 | Accuracy (%) | 99.8 |
| AA Omniscience - Health | 55.9 | Accuracy (%) | 99.7 |
| AA GDPval | 1751.06 | ELO | 99.6 |
| AA Omniscience - Business | 56.3 | Accuracy (%) | 99.6 |
| AA Omniscience - Humanities & Social Sciences | 64.1 | Accuracy (%) | 99.6 |
| AA CritPt | 31.14 | Accuracy (%) | 99.4 |
| AA Omniscience - Software Engineering (SWE) | 90.7 | Accuracy (%) | 99.4 |
| Artificial Analysis Intelligence Index | 53.8 | Intelligence Index | 99.4 |
| AA Omniscience | 42.38 | Score | 99 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1-adaptive-reasoning-xhigh-effort-default-fallback · How It Works · Data refreshed daily, snapshot 2026-09-05.