Compare AI models

Specifications
Parameters
7B1.5B/4B
Context window
8k8k
Benchmarks
MMLU
62.5%54.84%
GSM8K
36.5%54.89%
Overview
CompanyMistralZ.ai
Release dateSep 27 2023Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral 7B and GLM-Edge are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). Mistral 7B shipped 429 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

Mistral 7B has 7B parameters, while GLM-Edge has 1.5B/4B. Context windows are 8k (Mistral 7B) vs 8k (GLM-Edge).

On MMLU, Mistral 7B leads at 62.5% vs GLM-Edge at 54.84%. On GSM8K, GLM-Edge leads at 54.89% vs Mistral 7B at 36.5%.