Claude Sonnet 5 (Medium): benchmark results
Provider: Anthropic. Released 2026-06-30. Access: API.
Aggregate Rating 1739 ± 11, rank #263 of 2168 rated models, from 104 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| PetriBench - Boundedness (Hard) | 58 | Exact-Match Accuracy (%) | 91.4 |
| AA-Omniscience Index - Software Engineering (SWE) - Rust | 66 | Omniscience Index | 86.9 |
| Artificial Analysis Intelligence Index | 28.05 | Intelligence Index | 80.1 |
| AA-Omniscience Index - Software Engineering (SWE) - Swift | 40 | Omniscience Index | 79 |
| AA-Omniscience Index - Software Engineering (SWE) - Kotlin | 26 | Omniscience Index | 78.6 |
| AA-Omniscience Index - Software Engineering (SWE) - HTML | 40 | Omniscience Index | 78.4 |
| AA-Omniscience Index - Software Engineering (SWE) - Go | 24 | Omniscience Index | 77.2 |
| AA CritPt | 8.57 | Accuracy (%) | 76.8 |
| AA Humanity's Last Exam | 29.98 | Accuracy (%) | 76.8 |
| AA-Omniscience Index - Software Engineering (SWE) - JavaScript | 26.36 | Omniscience Index | 76.1 |
| AA-Omniscience Accuracy | 37.1 | Accuracy (%) | 75 |
| AA-Omniscience Index - Software Engineering (SWE) - Python | 18.5 | Omniscience Index | 74.5 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-medium · How It Works · Data refreshed daily, snapshot 2026-10-20.