models · mistralai
Compact Magistral reasoning model. Efficient thinking at 24B params.
| Method | closed-weights |
|---|
| Publisher | mistralai |
|---|---|
| Origin | France |
| Licence | Apache-2.0 |
| Pulls recorded here | 39,009 |
| MMLU-Pro | 74.6 |
|---|---|
| GPQA Diamond | 64.1 |
| AIME 2025 | 41.3 |
| MATH-500 | 96.3 |
| LiveCodeBench | 51.4 |
| IFBench | 24.8 |
| Humanity's Last Exam | 7.6 |
Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.
Registry record as of 2026-10-14. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.