Compare AI models

Specifications
Parameters
24B7B/14B
Context window
128k1M
API pricing
Cheapest input
$0.06DeepInfra—
Cheapest output
$0.16DeepInfra—
$25.00DeepInfra · fp8—
Benchmarks
MATH
69.42%79.5%
MMLU-Pro
69.06%63.3%
Overview
CompanyMistralQwen
Release dateJun 20 2025Jan 27 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Mistral Small 3.2 and Qwen2.5-1M are evenly matched across the 2 benchmarks they both report (MATH, MMLU-Pro). Qwen2.5-1M shipped 144 days before Mistral Small 3.2, so benchmark comparisons should account for the intervening progress.

Mistral Small 3.2 has 24B parameters, while Qwen2.5-1M has 7B/14B. Context windows are 128k (Mistral Small 3.2) vs 1M (Qwen2.5-1M).

On MATH, Qwen2.5-1M leads at 79.5% vs Mistral Small 3.2 at 69.42%. On MMLU-Pro, Mistral Small 3.2 leads at 69.06% vs Qwen2.5-1M at 63.3%.