Compare AI models

Specifications
Parameters
—6B
Context window
32k8k
Benchmarks
HumanEval
45.1%35.9%
Overview
CompanyMistralZ.ai
Release dateFeb 26 2024Jul 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 216 days before Mistral Large, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Large) vs 8k (CodeGeeX2-6B). Mistral Large is closed, while CodeGeeX2-6B is open weight.

On HumanEval, Mistral Large leads at 45.1% vs CodeGeeX2-6B at 35.9%.