Compare AI models

Specifications
Parameters
—1.5B/4B
Context window
32k8k
Benchmarks
MMLU
81.2%54.84%
GSM8K
81%54.89%
Overview
CompanyMistralZ.ai
Release dateFeb 26 2024Nov 29 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large leads GLM-Edge on 2 of the 2 benchmarks they both report (MMLU, GSM8K). Mistral Large shipped 277 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Large) vs 8k (GLM-Edge). Mistral Large is closed, while GLM-Edge is open weight.

On MMLU, Mistral Large leads at 81.2% vs GLM-Edge at 54.84%. On GSM8K, Mistral Large leads at 81% vs GLM-Edge at 54.89%.