2 vs 0 benchmarks won
Anthropic Claude Opus 4.7 | Mistral Devstral 2 (123B) | |
|---|---|---|
| Overview | ||
| Company | Anthropic | Mistral |
| Release date | Apr 16 2026 | Dec 9 2025 |
| Model type | — | — |
| Open source | No | Yes |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 94.2% | — |
Software engineering SWE-Bench Verified | 87.6% | — |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Devstral 2 (123B) shipped 128 days before Claude Opus 4.7 | |
Claude Opus 4.7 leads Devstral 2 (123B) on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Devstral 2 (123B) shipped 128 days before Claude Opus 4.7, so benchmark comparisons should account for the intervening progress.
Devstral 2 (123B) is an open-source / open-weight model; Claude Opus 4.7 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.