Compare AI models

Specifications
Parameters
7B6B
Context window
256k32k
Benchmarks
HumanEval
75%9.8%
Overview
CompanyMistralZ.ai
Release dateJul 16 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Codestral Mamba 7B leads ChatGLM2-6B on 1 of the 1 benchmark they both report (HumanEval). ChatGLM2-6B shipped 387 days before Codestral Mamba 7B, so benchmark comparisons should account for the intervening progress.

Codestral Mamba 7B has 7B parameters, while ChatGLM2-6B has 6B. Context windows are 256k (Codestral Mamba 7B) vs 32k (ChatGLM2-6B).

On HumanEval, Codestral Mamba 7B leads at 75% vs ChatGLM2-6B at 9.8%.