Compare AI models

Specifications
Parameters
—6B
Context window
256k32k
Benchmarks
HumanEval
86.6%9.8%
Overview
CompanyMistralZ.ai
Release dateJan 13 2025Jun 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Codestral 25.01 leads ChatGLM2-6B on 1 of the 1 benchmark they both report (HumanEval). ChatGLM2-6B shipped 568 days before Codestral 25.01, so benchmark comparisons should account for the intervening progress.

Context windows are 256k (Codestral 25.01) vs 32k (ChatGLM2-6B). Codestral 25.01 is closed, while ChatGLM2-6B is open weight.

On HumanEval, Codestral 25.01 leads at 86.6% vs ChatGLM2-6B at 9.8%.