Claude Sonnet 5 (Max) — benchmark results
Claude Sonnet 5 evaluated at the max reasoning-effort setting. Provider: Anthropic. Released 2026-06-30. Access: API.
Unified ELO 2007 ± 34, rank #22 of 1776 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Vals AI ProofBench | 66 | Accuracy (%) | 87.1 |
| Epoch AI - Scicode | 53.59 | Score | 80.9 |
| Epoch AI - ECI | 153.2 | ECI Score | 80 |
| Epoch AI - Critpt | 16.86 | Score | 77.5 |
| CursorBench 3.1 | 61.5 | Score (%) | 64.9 |
| Epoch AI - Cursorbench | 61.2 | Score | 63 |
| FrontierMath - Tiers 1-3 (v2) | 65.61 | Accuracy (%, 285 private v2 problems) | 62.2 |
| FrontierMath - Tier 4 (v2) | 29.27 | Accuracy (%, 41 private v2 problems) | 57.7 |
| AutomationBench | 13.5 | Pass Rate (%) | 0 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-max · How the rankings work · Data refreshed daily, snapshot 2026-07-22.