Compare AI models

Specifications
Parameters
24B—
Context window
32k128k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.064DeepInfra—
$14.00DeepInfra · fp8—
Benchmarks
HumanEval
84.8%75.7%
IFEval
82.9%75.2%
MATH
70.6%57.9%
Overview
CompanyMistralZ.ai
Release dateJan 30 2025Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Mistral Small 3 leads GLM-4-Air on 3 of the 3 benchmarks they both report (HumanEval, IFEval, MATH). GLM-4-Air shipped 239 days before Mistral Small 3, so benchmark comparisons should account for the intervening progress.

Context windows are 32k (Mistral Small 3) vs 128k (GLM-4-Air). Mistral Small 3 is open weight, while GLM-4-Air is closed.

On HumanEval, Mistral Small 3 leads at 84.8% vs GLM-4-Air at 75.7%. On IFEval, Mistral Small 3 leads at 82.9% vs GLM-4-Air at 75.2%. On MATH, Mistral Small 3 leads at 70.6% vs GLM-4-Air at 57.9%.