Claude 3.7 Sonnet (Non-reasoning) — benchmark results
Claude 3.7 Sonnet evaluated with reasoning disabled. Provider: Anthropic. Released 2025-02-24. Access: API.
Unified ELO 1605 ± 29, rank #470 of 1776 rated models, from 38 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Omniscience - Law | 30.1 | Accuracy (%) | 86.4 |
| AA Omniscience - Business | 29.4 | Accuracy (%) | 83.5 |
| AA Omniscience | -9.23 | Score | 80.5 |
| AA Omniscience - Humanities & Social Sciences | 28.9 | Accuracy (%) | 77.2 |
| AA-Omniscience Accuracy | 28.3 | Accuracy (%) | 76.1 |
| AA Omniscience - Software Engineering (SWE) - Java | 26 | Accuracy (%) | 74.7 |
| AA Omniscience - Software Engineering (SWE) - Go | 30 | Accuracy (%) | 74.3 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 30 | Accuracy (%) | 74.1 |
| AA Omniscience - Software Engineering (SWE) - HTML | 44 | Accuracy (%) | 72.1 |
| AA Omniscience - Software Engineering (SWE) - R | 22 | Accuracy (%) | 69.4 |
| AA MMLU-Pro | 80.33 | Accuracy (%) | 68.3 |
| AA Omniscience - Software Engineering (SWE) - Python | 28.5 | Accuracy (%) | 67.5 |
Interactive version: theaggregate.ai/model?slug=claude-3-7-sonnet-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.