Compare AI models

Specifications
Parameters
24B—
Context window
128k—
API pricing
Cheapest input
$0.351Cloudflare—
Cheapest output
$0.555Cloudflare—
$97.95Cloudflare—
Benchmarks
HumanEval
88.41%72%
MATH
69.3%47.9%
MMLU
80.62%81.5%
Overview
CompanyMistralZ.ai
Release dateMar 17 2025Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Mistral Small 3.1 leads GLM-4 on 2 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). GLM-4 shipped 426 days before Mistral Small 3.1, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.1 is open weight, while GLM-4 is closed.

On HumanEval, Mistral Small 3.1 leads at 88.41% vs GLM-4 at 72%. On MATH, Mistral Small 3.1 leads at 69.3% vs GLM-4 at 47.9%. On MMLU, GLM-4 leads at 81.5% vs Mistral Small 3.1 at 80.62%.