1 vs 2 benchmarks won
Anthropic Claude Sonnet 4.5 | OpenAI GPT-5.1 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | OpenAI |
| Release date | Sep 29 2025 | Nov 12 2025 |
| Model type | — | — |
| Open source | No | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 83.4% | 88.1% |
Software engineering SWE-Bench Verified | 77.2% | 76.3% |
Multimodal understanding MMMU | 68% | 76% |
| Timeline | ||
| Release gap | Claude Sonnet 4.5 shipped 44 days before GPT-5.1 | |
GPT-5.1 leads Claude Sonnet 4.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Sonnet 4.5 shipped 44 days before GPT-5.1, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, GPT-5.1 scores 88.1%, 4.7 points above Claude Sonnet 4.5 at 83.4%. On SWE-Bench Verified, Claude Sonnet 4.5 scores 77.2%, 0.9 points above GPT-5.1 at 76.3%. On MMMU, GPT-5.1 scores 76%, 8 points above Claude Sonnet 4.5 at 68%.