0 vs 2 benchmarks won
Mistral Devstral 2 (123B) | OpenAI GPT-5.2 | |
|---|---|---|
| Overview | ||
| Company | Mistral | OpenAI |
| Release date | Dec 9 2025 | Dec 11 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 92.4% |
Software engineering SWE-Bench Verified | — | 80% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | Devstral 2 (123B) shipped 2 days before GPT-5.2 | |
GPT-5.2 leads Devstral 2 (123B) on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Devstral 2 (123B) shipped 2 days before GPT-5.2, so benchmark comparisons should account for the intervening progress.
Devstral 2 (123B) is an open-source / open-weight model; GPT-5.2 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.