Claude Opus 4.7
Latest flagship Anthropic model.
Benchmark results
| Benchmark | Category | Score | Verified | Source |
|---|---|---|---|---|
| GPQA Diamond | reasoning | 83.3% | yes | |
| HumanEval | coding | 95.0% | yes | |
| MMMU | multimodal | 76.1% | yes | |
| SWE-bench Verified | coding | 74.5% | yes |
Latest flagship Anthropic model.
| Benchmark | Category | Score | Verified | Source |
|---|---|---|---|---|
| GPQA Diamond | reasoning | 83.3% | yes | |
| HumanEval | coding | 95.0% | yes | |
| MMMU | multimodal | 76.1% | yes | |
| SWE-bench Verified | coding | 74.5% | yes |