Compare AI models

Specifications
Parameters
3B—
Context window
128k—
Benchmarks
HumanEval
77.4%72%
MATH
51.7%47.9%
Overview
CompanyMistralZ.ai
Release dateOct 16 2024Jan 16 2024
AccessClosedClosed
Model detailsView modelView model

Frequently asked questions

Ministral 3B leads GLM-4 on 2 of the 2 benchmarks they both report (HumanEval, MATH). GLM-4 shipped 274 days before Ministral 3B, so benchmark comparisons should account for the intervening progress.

Published specifications for these two models are limited — see each model page for the latest details.

On HumanEval, Ministral 3B leads at 77.4% vs GLM-4 at 72%. On MATH, Ministral 3B leads at 51.7% vs GLM-4 at 47.9%.