Compare AI models

Specifications
Parameters
—6B
Context window
32k32k
Benchmarks
HumanEval
45.1%9.8%
HellaSwag
89.2%57%
MMLU
81.2%45.2%
GSM8K
81%25.9%
Overview
CompanyMistralZ.ai
Release dateFeb 26 2024Jun 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large leads ChatGLM2-6B on 4 of the 4 benchmarks they both report (HumanEval, HellaSwag, MMLU, GSM8K). ChatGLM2-6B shipped 246 days before Mistral Large, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Large) vs 32k (ChatGLM2-6B). Mistral Large is closed, while ChatGLM2-6B is open weight.

On HumanEval, Mistral Large leads at 45.1% vs ChatGLM2-6B at 9.8%. On HellaSwag, Mistral Large leads at 89.2% vs ChatGLM2-6B at 57%. On MMLU, Mistral Large leads at 81.2% vs ChatGLM2-6B at 45.2%. On GSM8K, Mistral Large leads at 81% vs ChatGLM2-6B at 25.9%.