models · mistralai

Magistral Small

Compact Magistral reasoning model. Efficient thinking at 24B params.

What this registry has checked

Closed. A third party reports this model and we have recorded their numbers. Nothing of our own: no weights seen, no publisher hash held. Treat every figure here as their claim.
Methodclosed-weights

What is recorded

Publishermistralai
OriginFrance
LicenceApache-2.0
Pulls recorded here39,009

Reported scores

MMLU-Pro74.6
GPQA Diamond64.1
AIME 202541.3
MATH-50096.3
LiveCodeBench51.4
IFBench24.8
Humanity's Last Exam7.6

Reported by a third party and recorded here, not re-run by us. Source: artificialanalysis.ai/api/v2.

Elsewhere in the registry

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.