2 vs 0 benchmarks won
Anthropic Claude Opus 4.6 | Mistral Mistral Medium 3.5 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Feb 5 2026 | Apr 29 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 128B |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 91.3% | — |
Software engineering SWE-Bench Verified | 80.8% | 77.6% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude Opus 4.6 shipped 83 days before Mistral Medium 3.5 | |
Claude Opus 4.6 leads Mistral Medium 3.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Claude Opus 4.6 shipped 83 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; Claude Opus 4.6 is proprietary.
On SWE-Bench Verified, Claude Opus 4.6 scores 80.8%, 3.2 points above Mistral Medium 3.5 at 77.6%.