Compare AI models

Specifications
Parameters
7B—
Context window
8k—
Benchmarks
HumanEval
26.2%72%
MMLU
62.5%81.5%
GSM8K
36.5%87.6%
Overview
CompanyMistralZ.ai
Release dateSep 27 2023Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4 leads Mistral 7B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Mistral 7B shipped 111 days before GLM-4, so benchmark comparisons should account for the intervening progress.

Mistral 7B is open weight, while GLM-4 is closed.

On HumanEval, GLM-4 leads at 72% vs Mistral 7B at 26.2%. On MMLU, GLM-4 leads at 81.5% vs Mistral 7B at 62.5%. On GSM8K, GLM-4 leads at 87.6% vs Mistral 7B at 36.5%.