Compare AI models

Specifications
Parameters
24B14B
Context window
128k2k
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.16DeepInfra—
$25.00DeepInfra · fp8—
Benchmarks
MATH
69.42%24.8%
MMLU
80.5%66.3%
Overview
CompanyMistralQwen
Release dateJun 20 2025Sep 25 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 3.2 leads Qwen-14B on 2 of the 2 benchmarks they both report (MATH, MMLU). Qwen-14B shipped 634 days before Mistral Small 3.2, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.2 has 24B parameters, while Qwen-14B has 14B. Context windows are 128k (Mistral Small 3.2) vs 2k (Qwen-14B).

On MATH, Mistral Small 3.2 leads at 69.42% vs Qwen-14B at 24.8%. On MMLU, Mistral Small 3.2 leads at 80.5% vs Qwen-14B at 66.3%.