Claude Sonnet 5 (xHigh): benchmark results
Claude Sonnet 5 evaluated at the xhigh reasoning-effort setting. Provider: Anthropic. Released 2026-06-30. Access: API.
Aggregate Rating 1793 ± 11, rank #151 of 2168 rated models, from 128 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LiveBench Logic With Navigation | 86 | Score | 94.3 |
| RuBench (Fresh-11) | 75.8 | Pass@1 (%; the 11 tasks with fix commits after 2026-06-17, e | 88.9 |
| AA-Omniscience Index - Software Engineering (SWE) - Julia | 36 | Omniscience Index | 88.2 |
| LiveBench Spatial | 100 | Score | 87.9 |
| Epoch AI - GPQA Diamond | 90.53 | Accuracy (%) | 87.2 |
| Artificial Analysis Intelligence Index | 34.38 | Intelligence Index | 86.6 |
| AA-Omniscience Index - Software Engineering (SWE) - Swift | 52 | Omniscience Index | 86.5 |
| LiveBench Code Generation | 83.1 | Score | 86.4 |
| AA Humanity's Last Exam | 39.02 | Accuracy (%) | 85.9 |
| AA CritPt | 15.43 | Accuracy (%) | 84.5 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 34 | Omniscience Index | 83.4 |
| EnterpriseOps-Gym-AA - Teams | 48 | Task Success (%) | 82.7 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-xhigh · How It Works · Data refreshed daily, snapshot 2026-10-20.