Claude Sonnet 5 (Adaptive Reasoning, Max Effort): benchmark results
Claude Sonnet 5 evaluated in adaptive-reasoning mode at max effort. Provider: Anthropic. Released 2026-06-30. Access: API.
Unified ELO 1668 ± 1, rank #188 of 1761 rated models, from 24 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Long Context Reasoning | 82 | Accuracy (%) | 94.9 |
| UGI - Writing | 62.71 | Writing Score | 94.1 |
| Artificial Analysis Intelligence Index | 45.11 | Intelligence Index | 93.8 |
| AA Humanity's Last Exam | 41.29 | Accuracy (%) | 92.2 |
| AA GPQA Diamond | 91.11 | Accuracy (%) | 91.7 |
| UGI - Natural Intelligence | 53.88 | NatInt Score | 91.5 |
| AA Omniscience | 16.45 | Score | 90.4 |
| AA CritPt | 16.86 | Accuracy (%) | 90.1 |
| AA Omniscience - Science, Engineering & Mathematics | 45.52 | Accuracy (%) | 88.3 |
| AA-LCR | 77 | Accuracy (self-reported) | 87.4 |
| AA GDPval | 1505.81 | ELO | 86.9 |
| AA Omniscience - Software Engineering (SWE) | 62.7 | Accuracy (%) | 85.2 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-adaptive-reasoning-max-effort · How It Works · Data refreshed daily, snapshot 2026-09-05.