Compare AI models

Specifications
Parameters
8B—
Context window
128k128k
Benchmarks
HumanEval
76.8%75.7%
MATH
54.5%57.9%
Overview
CompanyMistralZ.ai
Release dateOct 16 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Ministral 8B and GLM-4-Air are evenly matched across the 2 benchmarks they both report (HumanEval, MATH). GLM-4-Air shipped 133 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Ministral 8B) vs 128k (GLM-4-Air). Ministral 8B is open weight, while GLM-4-Air is closed.

On HumanEval, Ministral 8B leads at 76.8% vs GLM-4-Air at 75.7%. On MATH, GLM-4-Air leads at 57.9% vs Ministral 8B at 54.5%.