Compare AI models

Specifications
Parameters
7B—
Context window
8k128k
Benchmarks
HumanEval
26.2%75.7%
MMLU
62.5%81.9%
GSM8K
36.5%90.9%
Overview
CompanyMistralZ.ai
Release dateSep 27 2023Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4-Air leads Mistral 7B on 3 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). Mistral 7B shipped 252 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 8k (Mistral 7B) vs 128k (GLM-4-Air). Mistral 7B is open weight, while GLM-4-Air is closed.

On HumanEval, GLM-4-Air leads at 75.7% vs Mistral 7B at 26.2%. On MMLU, GLM-4-Air leads at 81.9% vs Mistral 7B at 62.5%. On GSM8K, GLM-4-Air leads at 90.9% vs Mistral 7B at 36.5%.