Compare AI models

Specifications
Parameters
12B6B
Context window
128k32k
Benchmarks
HumanEval
72%9.8%
MATH
48.1%6.9%
MMLU
69.2%45.2%
Overview
CompanyMistralZ.ai
Release dateSep 11 2024Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Pixtral 24.09 leads ChatGLM2-6B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). ChatGLM2-6B shipped 444 days before Pixtral 24.09, so benchmark comparisons should account for the intervening progress.

Pixtral 24.09 has 12B parameters, while ChatGLM2-6B has 6B. Context windows are 128k (Pixtral 24.09) vs 32k (ChatGLM2-6B).

On HumanEval, Pixtral 24.09 leads at 72% vs ChatGLM2-6B at 9.8%. On MATH, Pixtral 24.09 leads at 48.1% vs ChatGLM2-6B at 6.9%. On MMLU, Pixtral 24.09 leads at 69.2% vs ChatGLM2-6B at 45.2%.