Compare AI models

Specifications
Parameters
24B14.3B
Context window
128k32k
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.16DeepInfra—
$25.00DeepInfra · fp8—
Benchmarks
MMLU
80.5%62.5%
Overview
CompanyMistralQwen
Release dateJun 20 2025Mar 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 3.2 leads Qwen1.5-MoE on 1 of the 1 benchmark they both report (MMLU). Qwen1.5-MoE shipped 449 days before Mistral Small 3.2, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.2 has 24B parameters, while Qwen1.5-MoE has 14.3B. Context windows are 128k (Mistral Small 3.2) vs 32k (Qwen1.5-MoE).

On MMLU, Mistral Small 3.2 leads at 80.5% vs Qwen1.5-MoE at 62.5%.