Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback): benchmark results
Provider: Anthropic. Released 2026-09-01. Access: API.
Unified ELO 1801 ± 1, rank #5 of 1761 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA GDPval | 1769.1 | ELO | 100 |
| AA Humanity's Last Exam | 59.13 | Accuracy (%) | 100 |
| AA Omniscience - Health | 57.4 | Accuracy (%) | 100 |
| AA Omniscience - Humanities & Social Sciences | 66.1 | Accuracy (%) | 100 |
| AA Omniscience - Science, Engineering & Mathematics | 62 | Accuracy (%) | 100 |
| AA Omniscience - Software Engineering (SWE) | 92.4 | Accuracy (%) | 100 |
| AA SciCode | 63.08 | Accuracy (%) | 100 |
| AA-Briefcase | 61.52 | Rubric Pass Rate (%) | 100 |
| AA-Omniscience Accuracy | 67.23 | Accuracy (%) | 100 |
| Artificial Analysis Intelligence Index | 56.76 | Intelligence Index | 100 |
| Epoch AI - Scicode | 62.04 | Score | 100 |
| AA Long Context Reasoning | 85.33 | Accuracy (%) | 99.8 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1-adaptive-reasoning-max-effort-default-fallback · How It Works · Data refreshed daily, snapshot 2026-09-05.