Claude Fable 5.1 (xHigh): benchmark results
Provider: Anthropic. Released 2026-09-01. Access: API.
Unified ELO 1792 ± 1, rank #9 of 1761 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SEAL - Humanity's Last Exam | 46.5 | Score | 100 |
| Epoch AI - Critpt | 31.14 | Score | 99.4 |
| CursorBench 3.1 | 72.8 | Score (%) | 98.6 |
| SEAL - Humanity's Last Exam (Text Only) | 46.8 | Score | 98.3 |
| ARC-AGI-2 | 90 | Accuracy (%) | 96.8 |
| ARC-AGI-1 | 96.5 | Accuracy (%) | 93.6 |
| LLM2014 Logic 2026-09 | 63.47 | Median Score | 90.9 |
| SEAL - Professional Reasoning Benchmark - Legal | 51.6 | Score | 87.1 |
| SEAL - Professional Reasoning Benchmark - Finance | 50.8 | Score | 80.6 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1-xhigh · How It Works · Data refreshed daily, snapshot 2026-09-05.