Compare AI models

Specifications
Parameters
24B6B
Context window
128k32k
API pricing
Cheapest input
$0.351Cloudflare—
Cheapest output
$0.555Cloudflare—
$97.95Cloudflare—
Benchmarks
HumanEval
88.41%9.8%
MATH
69.3%6.9%
MMLU
80.62%45.2%
Overview
CompanyMistralZ.ai
Release dateMar 17 2025Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 3.1 leads ChatGLM2-6B on 3 of the 3 benchmarks they both report (HumanEval, MATH, MMLU). ChatGLM2-6B shipped 631 days before Mistral Small 3.1, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.1 has 24B parameters, while ChatGLM2-6B has 6B. Context windows are 128k (Mistral Small 3.1) vs 32k (ChatGLM2-6B).

On HumanEval, Mistral Small 3.1 leads at 88.41% vs ChatGLM2-6B at 9.8%. On MATH, Mistral Small 3.1 leads at 69.3% vs ChatGLM2-6B at 6.9%. On MMLU, Mistral Small 3.1 leads at 80.62% vs ChatGLM2-6B at 45.2%.