Compare AI models

Specifications
Parameters
24B1.5B/7B/72B
Context window
32k4k
API pricing
Cheapest input
$0.04DeepInfra—
Cheapest output
$0.064DeepInfra—
$14.00DeepInfra · fp8—
Benchmarks
MATH
70.6%85.9%
Overview
CompanyMistralQwen
Release dateJan 30 2025Sep 19 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen2.5-Math leads Mistral Small 3 on 1 of the 1 benchmark they both report (MATH). Qwen2.5-Math shipped 133 days before Mistral Small 3, so benchmark comparisons should account for the intervening progress.

Mistral Small 3 has 24B parameters, while Qwen2.5-Math has 1.5B/7B/72B. Context windows are 32k (Mistral Small 3) vs 4k (Qwen2.5-Math).

On MATH, Qwen2.5-Math leads at 85.9% vs Mistral Small 3 at 70.6%.