Anthropic
Claude Sonnet 5 benchmark results
7 results on 5 benchmarks from 2 sources.
Also listed as: claude-sonnet-5-high · claude-sonnet-5_max · Claude Sonnet 5 (max) · claude-sonnet-5_xhigh · Claude Sonnet 5 (xhigh)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1461 | 57 | Overall, style control on; 47576 votes; 95% CI 1457–1465“claude-sonnet-5-high” | Official leaderboard | Oct 8, 2026 |
| LMArena WebDev | 1541 | 43 | Overall; 14574 votes; 95% CI 1535–1547“claude-sonnet-5-high” | Official leaderboard | Oct 8, 2026 |
| LMArena Vision | 1265 | 39 | Overall, style control on; 13029 votes; 95% CI 1257–1271“claude-sonnet-5-high” | Official leaderboard | Oct 2, 2026 |
| GPQA Diamond | 90.5% | 37 | Epoch AI run, accuracy; effort: xhigh | Independent run | Jul 1, 2026 |
| GPQA Diamond | 80.3% | 114 | Epoch AI run, accuracy; effort: max | Independent run | Aug 6, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 94.7% | 51 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: xhigh | Independent run | Jul 1, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 80.0% | 110 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: max | Independent run | Aug 6, 2026 |
FAQ
Where do these Claude Sonnet 5 scores come from?
From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.