1 vs 1 benchmarks won
Anthropic Claude Haiku 4.5 | Mistral Mistral Medium 3.5 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Oct 15 2025 | Apr 29 2026 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | 128B |
Context window | — | 256k |
| Benchmarks | ||
Science reasoning GPQA Diamond | 73% | — |
Software engineering SWE-Bench Verified | 73.3% | 77.6% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Claude Haiku 4.5 shipped 196 days before Mistral Medium 3.5 | |
Claude Haiku 4.5 and Mistral Medium 3.5 are evenly matched across the benchmarks they both publish. Claude Haiku 4.5 shipped 196 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 Haiku 4.5 is proprietary.
On SWE-Bench Verified, Mistral Medium 3.5 scores 77.6%, 4.3 points above Claude Haiku 4.5 at 73.3%.