1 vs 2 benchmarks won
Mistral Mistral Medium 3.5 | OpenAI GPT-5.1 | |
|---|---|---|
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Apr 29 2026 | Nov 12 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 128B | — |
Context window | 256k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 88.1% |
Software engineering SWE-Bench Verified | 77.6% | 76.3% |
Multimodal understanding MMMU | — | 76% |
| Timeline | ||
| Release gap | GPT-5.1 shipped 168 days before Mistral Medium 3.5 | |
GPT-5.1 leads Mistral Medium 3.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). GPT-5.1 shipped 168 days before Mistral Medium 3.5, so benchmark comparisons should account for the intervening progress.
Mistral Medium 3.5 is an open-source / open-weight model; GPT-5.1 is proprietary.
On SWE-Bench Verified, Mistral Medium 3.5 scores 77.6%, 1.3 points above GPT-5.1 at 76.3%.