Claude Sonnet 4.6 (Medium) — benchmark results
Provider: Anthropic. Released 2026-02-17. Access: API.
Unified ELO 1800 ± 33, rank #163 of 1839 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| ALE-Bench | 1327.3 | Performance (Self-Refine x1) (self-reported) | 94.9 |
| WeirdML | 66.07 | Average Score | 81.3 |
| Epoch AI - ECI | 152.35 | ECI Score | 74.6 |
| OTIS Mock AIME 2024-25 | 82.22 | Accuracy (%) | 65.7 |
| GIM | 0.84 | IRT ability (theta) | 64.4 |
| Opus Magnum Bench | 12.37 | Human-normalized score (%) | 23.8 |
| Chess Puzzles (Epoch AI) | 8 | Accuracy (%) | 16.9 |
| Epoch AI - Cursorbench | 46 | Score | 3.3 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-6-medium · How It Works · Data refreshed daily, snapshot 2026-08-05.