Compare AI models

Specifications
Parameters
7B—
Context window
32k—
Benchmarks
MATH
56.6%47.9%
GSM8K
77.1%87.6%
Overview
CompanyMistralZ.ai
Release dateJul 16 2024Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Mathstral 7B and GLM-4 are evenly matched across the 2 benchmarks they both report (MATH, GSM8K). GLM-4 shipped 182 days before Mathstral 7B, so benchmark comparisons should account for the intervening progress.

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

On MATH, Mathstral 7B leads at 56.6% vs GLM-4 at 47.9%. On GSM8K, GLM-4 leads at 87.6% vs Mathstral 7B at 77.1%.