Ministral 3 14B Reasoning

Mistral AI llm

Edge-sized open-weight reasoning model from the Mistral 3 launch, aimed at offline and on-device deployment.

overall ⌄

47.5

64 of 125 ranked

price · $/M tokens

0.2 / 0.2

in / out, as of 2026-07-25

to run it yourself ⌄

8 GB

minimum · 34 GB recommended

Benchmarks

What its maker published, and what anyone else measured. Every figure links the document it came from.

benchmarkpublishedmeasured
AIME 202585 —

Cheaper, and at least as good

Nothing is both cheaper and ranked as high. This model is on the value frontier — whatever you pay for it, you are paying for something.

Lineage

No recorded lineage — root or standalone model.

view in full graph →

Metadata

orgMistral AI
released2025-12-02
params14B
licenseapache-2.0
hf idmistralai/Ministral-3-14B-Reasoning-2512