Compare AI models

Specifications
Parameters
7B—
Context window
32k—
Benchmarks
HumanEval
38.4%72%
MATH
13.2%47.9%
Overview
CompanyMistralZ.ai
Release dateMay 22 2024Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4 leads Mistral 7B v0.3 on 2 of the 2 benchmarks they both report (HumanEval, MATH). GLM-4 shipped 127 days before Mistral 7B v0.3, so benchmark comparisons should account for the intervening progress.

Mistral 7B v0.3 is open weight, while GLM-4 is closed.

On HumanEval, GLM-4 leads at 72% vs Mistral 7B v0.3 at 38.4%. On MATH, GLM-4 leads at 47.9% vs Mistral 7B v0.3 at 13.2%.