Ministral 3 3B Reasoning 2512
Mistral AI · 2025-12-02 · 4.3B parameters
Ministral 3 3B Reasoning 2512 is the reasoning post-trained checkpoint of Mistral AI's December 2025 Ministral 3 3B, released alongside the separate Base and non-reasoning Instruct checkpoints for edge and local deployment. The open-weight Apache-2.0 model combines a 3.4B language model with a 0.4B vision encoder, accepts text and image input, produces text with always-on reasoning traces for math, coding and STEM tasks, and supports a 262,144-token context.
Benchmark scores
| Benchmark | Score |
|---|---|
| MultiChallenge | 25.7 |