Claude Fable 5.1 (Medium): benchmark results
Provider: Anthropic. Released 2026-09-01. Access: API.
Unified ELO 1783 ± 1, rank #12 of 3078 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Conceptual Reasoning Index | 74.95 | Chance-Corrected Score (0-100) | 100 |
| Conceptual Reasoning Index - Argument Evaluation (LMCA) | 65.32 | Chance-Corrected Score (0-100) | 99.6 |
| Conceptual Reasoning Index - Consistency (ACCoRD) | 83.67 | Chance-Corrected Score (0-100) | 98.9 |
| DuelLab Overall | 77.2 | DuelLab Score | 97.5 |
| Conceptual Reasoning Index - Decision Theory (DTBench) | 95.12 | Chance-Corrected Score (0-100) | 95.6 |
| Epoch AI - Critpt | 29.14 | Score | 94.3 |
| Maze-Bench | 55.35 | Mean Score | 93.8 |
| ARC-AGI-2 | 86.25 | Accuracy (%) | 93.3 |
| CursorBench 4.0 | 46.8 | Score (%) | 92.1 |
| ARC-AGI-1 | 94.5 | Accuracy (%) | 88.6 |
| Epoch AI - Cursorbench | 68 | Score | 86.3 |
| AI Coding Daily (Claude Code) - Laravel Code Quality | 18.55 | Laravel Code Quality (max 20) points, LLM-judged rubric scor | 83.3 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-1-medium · How It Works · Data refreshed daily, snapshot 2026-09-19.