Compare AI models

Specifications
Parameters
24B—
Context window
32k—
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.064DeepInfra—
$14.00DeepInfra · fp8—
Benchmarks
HumanEval
84.8%72%
MATH
70.6%47.9%
Overview
CompanyMistralZ.ai
Release dateJan 30 2025Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Mistral Small 3 leads GLM-4 on 2 of the 2 benchmarks they both report (HumanEval, MATH). GLM-4 shipped 380 days before Mistral Small 3, so benchmark comparisons should account for the intervening progress.

Mistral Small 3 is open weight, while GLM-4 is closed.

On HumanEval, Mistral Small 3 leads at 84.8% vs GLM-4 at 72%. On MATH, Mistral Small 3 leads at 70.6% vs GLM-4 at 47.9%.