1 vs 1 benchmarks won
Mistral Mistral Medium 3.5 | OpenAI GPT-5.4 | |
|---|---|---|
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Apr 29 2026 | Mar 5 2026 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | 128B | — |
Context window | 256k | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 92.8% |
Software engineering SWE-Bench Verified | 77.6% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | GPT-5.4 shipped 55 days before Mistral Medium 3.5 | |
Mistral Medium 3.5 and GPT-5.4 are evenly matched across the benchmarks they both publish. GPT-5.4 shipped 55 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-5.4 is proprietary.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.