Claude Fable 5 (Adaptive Reasoning, Max Effort): benchmark results
Provider: Anthropic. Released 2026-06-09. Access: API.
Unified ELO 1751 ± 1, rank #29 of 1761 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| HANDBOOK.md Agents | 36.2 | Score (%) | 100 |
| UGI - Natural Intelligence | 76.72 | NatInt Score | 99.7 |
| UGI - Writing | 73.66 | Writing Score | 99.6 |
| GDP.pdf | 29.8 | Strict Pass Rate (%) | 96.3 |
| Riemann-bench | 60 | Score (%) | 91.9 |
| Chartography | 34.8 | Score (%) | 84.2 |
| UGI Leaderboard | 44.66 | UGI Score | 78.9 |
| UGI - Willingness (W/10) | 1.2 | W/10 Score | 3.9 |
| EnterpriseBench (CoreCraft Agents) | 70.3 | Score (%) | 0 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-adaptive-reasoning-max-effort · How It Works · Data refreshed daily, snapshot 2026-09-05.