Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...
| Benchmark | Score | Source |
|---|---|---|
| Chatbot Arena Elo | 1310 | |
| IFEval | 90.1 | |
| MMLU-Pro | 80.2 |
| Benchmark | Score | Source |
|---|---|---|
| HumanEval |
93.8 |
| SWE-bench Verified | 53.2 |
| Benchmark | Score | Source |
|---|---|---|
| BigBench-Hard | 90.8 | |
| GPQA Diamond | 70.5 |
| Benchmark | Score | Source |
|---|---|---|
| MMMU | 72.5 |
Anthropic