Compare AI models

Specifications
Parameters
141B1.5B/4B
Context window
64k8k
API pricing
Cheapest input
$2.00Mistral—
Cheapest output
$6.00Mistral—
$700Mistral · zdr—
Benchmarks
MMLU
77.75%54.84%
GSM8K
78.6%54.89%
Overview
CompanyMistralZ.ai
Release dateApr 10 2024Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mixtral 8×22B leads GLM-Edge on 2 of the 2 benchmarks they both report (MMLU, GSM8K). Mixtral 8×22B shipped 233 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

Mixtral 8×22B has 141B parameters, while GLM-Edge has 1.5B/4B. Context windows are 64k (Mixtral 8×22B) vs 8k (GLM-Edge).

On MMLU, Mixtral 8×22B leads at 77.75% vs GLM-Edge at 54.84%. On GSM8K, Mixtral 8×22B leads at 78.6% vs GLM-Edge at 54.89%.