Claude Sonnet 4 (Non-reasoning) — benchmark results
Claude Sonnet 4 evaluated with reasoning disabled. Provider: Anthropic. Released 2025-05-22. Access: API.
Unified ELO 1669 ± 22, rank #327 of 1776 rated models, from 49 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI - Writing | 63.68 | Writing Score | 95.4 |
| UGI - Natural Intelligence | 51.13 | NatInt Score | 91.2 |
| AA MMLU-Pro | 83.66 | Accuracy (%) | 85.8 |
| Confabulation Leaderboard (Lechmazur) | 5.45 | Confabulation rate % (lower is better) | 85.7 |
| AA Omniscience - Software Engineering (SWE) - Julia | 36 | Accuracy (%) | 84.6 |
| AA Omniscience - Software Engineering (SWE) - Dart | 36 | Accuracy (%) | 81.2 |
| AA Omniscience - Software Engineering (SWE) - Rust | 66 | Accuracy (%) | 80.6 |
| AA Omniscience | -9.23 | Score | 80.5 |
| AA Omniscience - Software Engineering (SWE) - Go | 34 | Accuracy (%) | 78.7 |
| AA Omniscience - Software Engineering (SWE) - C | 58 | Accuracy (%) | 78.3 |
| AA Omniscience - Software Engineering (SWE) | 38.9 | Accuracy (%) | 76.3 |
| AA Omniscience - Software Engineering (SWE) - Python | 35 | Accuracy (%) | 76.3 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-4-non-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.