Compare AI models

Specifications
Parameters
8B6B
Context window
128k32k
Benchmarks
HumanEval
76.8%9.8%
MATH
54.5%6.9%
Overview
CompanyMistralZ.ai
Release dateOct 16 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Ministral 8B leads ChatGLM2-6B on 2 of the 2 benchmarks they both report (HumanEval, MATH). ChatGLM2-6B shipped 479 days before Ministral 8B, so benchmark comparisons should account for the intervening progress.

Ministral 8B has 8B parameters, while ChatGLM2-6B has 6B. Context windows are 128k (Ministral 8B) vs 32k (ChatGLM2-6B).

On HumanEval, Ministral 8B leads at 76.8% vs ChatGLM2-6B at 9.8%. On MATH, Ministral 8B leads at 54.5% vs ChatGLM2-6B at 6.9%.