2 vs 0 benchmarks won
Anthropic Claude Haiku 4.5 | Mistral Mistral Large 2 | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Oct 15 2025 | Jul 24 2024 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 73% | — |
Software engineering SWE-Bench Verified | 73.3% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Mistral Large 2 shipped 448 days before Claude Haiku 4.5 | |
Claude Haiku 4.5 leads Mistral Large 2 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Mistral Large 2 shipped 448 days before Claude Haiku 4.5, so benchmark comparisons should account for the intervening progress.
Mistral Large 2 is an open-source / open-weight model; Claude Haiku 4.5 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.