Claude Fable 5.2 (Medium): benchmark results
Provider: Anthropic. Released 2026-11-09. Access: API.
Aggregate Rating 1999 ± 22, rank #5 of 2201 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI Coding Daily (Claude Code) - Laravel Code Quality | 19.13 | Laravel Code Quality (max 20) points, LLM-judged rubric scor | 100 |
| AI Coding Daily (Claude Code) - React-TS Code Quality | 19.5 | React-TS Code Quality (max 20) points, LLM-judged rubric sco | 100 |
| Conceptual Reasoning Index - Argument Evaluation (LMCA) | 70.03 | Chance-Corrected Score (0-100) | 98.9 |
| Conceptual Reasoning Index | 78.66 | Chance-Corrected Score (0-100) | 98.6 |
| DuelLab GameBench 2 - Reasoning Variants | 94.04 | GameBench2 normalized score (0–100) | 98.4 |
| Conceptual Reasoning Index - Decision Theory (DTBench) | 96.88 | Chance-Corrected Score (0-100) | 98.2 |
| Conceptual Reasoning Index - Consistency (ACCoRD) | 86.34 | Chance-Corrected Score (0-100) | 98.1 |
| Epoch AI - Dtbench | 98.13 | Score | 97.9 |
| Maze-Bench | 90.67 | Mean Score | 97.8 |
| ARC-AGI-3 | 73.32 | Accuracy (%) | 97.4 |
| Epoch AI - Critpt | 30.86 | Score | 94.4 |
| ARC-AGI-1 | 97.5 | Accuracy (%) | 93.4 |
Interactive version: theaggregate.ai/model?slug=claude-fable-5-2-medium · How It Works · Data refreshed daily, snapshot 2026-11-12.