Claude 3.5 Sonnet
Mid-tier Anthropic model.
Benchmark results
| Benchmark | Category | Score | Verified | Source |
|---|---|---|---|---|
| Chatbot Arena | general | 1271 | yes | |
| HumanEval | coding | 92.0% | yes | |
| MMLU | reasoning | 88.7% | yes | |
| MMMU | multimodal | 70.4% | yes | |
| SWE-bench Verified | coding | 49.0% | yes |
Mid-tier Anthropic model.
| Benchmark | Category | Score | Verified | Source |
|---|---|---|---|---|
| Chatbot Arena | general | 1271 | yes | |
| HumanEval | coding | 92.0% | yes | |
| MMLU | reasoning | 88.7% | yes | |
| MMMU | multimodal | 70.4% | yes | |
| SWE-bench Verified | coding | 49.0% | yes |