Magistral
modelReasoning model family trained with pure reinforcement learning — no distillation from external reasoning models. ~50% boost in AIME-24 (pass@1) over the Mistral Medium 3 base checkpoint.
RL on text maintains multimodal understanding, instruction following, and function calling. Magistral Small (24B, Apache 2.0) and Magistral Medium (proprietary).
Model Details
Architecture DENSE
AA Intelligence 12
Variants
| Name | Parameters | Notes |
|---|---|---|
| Magistral Small 1.2 | 24B | Apache 2.0 open weights; AA Intelligence Index 12, AAOI 50 |
| Magistral Medium 1.2 | — | Proprietary; AA Intelligence Index 20, AAOI 27.8 |