The mid-2024 Sonnet release that set the SOTA bar for coding and agents.
Anthropic's most intelligent model with significantly improved capabilities
| Benchmark | Claude 3.5 Sonnet |
|---|---|
| MMLU | 88.7% |
| HumanEval | 92.0% |
| MATH | 71.1% |
| SWE-bench Verified | 49.0% |
| GPQA Diamond | 59.4% |