Claude Sonnet 5 (Max) — benchmark results
Provider: Anthropic. Released 2026-06-30. Access: API.
Unified ELO 1985 ± 37, rank #27 of 1744 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Epoch AI - Scicode | 53.59 | Score | 88 |
| Epoch AI - Critpt | 16.86 | Score | 83.1 |
| Epoch AI - Cursorbench | 61.2 | Score | 65.4 |
| FrontierMath - Tiers 1-3 (v2) | 65.61 | Accuracy (%, 285 private v2 problems) | 62.9 |
| CursorBench 3.1 | 61.5 | Score (%) | 61.3 |
| FrontierMath - Tier 4 (v2) | 29.27 | Accuracy (%, 41 private v2 problems) | 59.7 |
| AutomationBench | 13.5 | Pass Rate (%) | 0 |
Interactive version: aibenchmarks.dev/model?slug=claude-sonnet-5-max · How the rankings work · Data refreshed daily, snapshot 2026-07-10.