Compare AI models

Specifications
Parameters
24B6B
Context window
128k32k
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.16DeepInfra—
$25.00DeepInfra · fp8—
Benchmarks
MATH
69.42%6.9%
MMLU
80.5%45.2%
Overview
CompanyMistralZ.ai
Release dateJun 20 2025Jun 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 3.2 leads ChatGLM2-6B on 2 of the 2 benchmarks they both report (MATH, MMLU). ChatGLM2-6B shipped 726 days before Mistral Small 3.2, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.2 has 24B parameters, while ChatGLM2-6B has 6B. Context windows are 128k (Mistral Small 3.2) vs 32k (ChatGLM2-6B).

On MATH, Mistral Small 3.2 leads at 69.42% vs ChatGLM2-6B at 6.9%. On MMLU, Mistral Small 3.2 leads at 80.5% vs ChatGLM2-6B at 45.2%.