Compare AI models

Specifications
Parameters
123B1.5B/4B
Context window
128k8k
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral—
Benchmarks
MMLU
84%54.84%
Overview
CompanyMistralZ.ai
Release dateJul 24 2024Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Large 2 leads GLM-Edge on 1 of the 1 benchmark they both report (MMLU). Mistral Large 2 shipped 128 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

Mistral Large 2 has 123B parameters, while GLM-Edge has 1.5B/4B. Context windows are 128k (Mistral Large 2) vs 8k (GLM-Edge).

On MMLU, Mistral Large 2 leads at 84% vs GLM-Edge at 54.84%.