Claude Sonnet 5 (Non-reasoning, High): benchmark results
Provider: Anthropic. Released 2026-06-30. Access: API.
Unified ELO 1624 ± 1, rank #340 of 1761 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 33.49 | Intelligence Index | 85.8 |
| AA Omniscience - Software Engineering (SWE) | 53.2 | Accuracy (%) | 82.1 |
| AA Omniscience | -0.65 | Score | 80.5 |
| AA-Omniscience Accuracy | 33.8 | Accuracy (%) | 77.6 |
| AA Omniscience - Humanities & Social Sciences | 31.6 | Accuracy (%) | 77.2 |
| AA Omniscience - Science, Engineering & Mathematics | 39.28 | Accuracy (%) | 77.1 |
| AA Omniscience - Business | 26.5 | Accuracy (%) | 76.8 |
| AA Omniscience - Health | 31.48 | Accuracy (%) | 76.8 |
| AA Omniscience - Law | 21.2 | Accuracy (%) | 72.1 |
| AA Humanity's Last Exam | 19.05 | Accuracy (%) | 70.7 |
| AA GDPval | 1288.23 | ELO | 69.2 |
| AA GPQA Diamond | 80 | Accuracy (%) | 67.2 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-non-reasoning-high · How It Works · Data refreshed daily, snapshot 2026-09-05.