Compare AI models

Specifications
Parameters
24B—
Context window
128k1M
API pricing
Cheapest input
$0.351Cloudflare—
Cheapest output
$0.555Cloudflare—
$97.95Cloudflare—
Benchmarks
HumanEval
88.41%86.6%
MATH
69.3%81.1%
MMLU-Pro
66.76%64.5%
Overview
CompanyMistralQwen
Release dateMar 17 2025Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Mistral Small 3.1 leads Qwen2.5-Turbo (1M) on 2 of the 3 benchmarks they both report (HumanEval, MATH, MMLU-Pro). Qwen2.5-Turbo (1M) shipped 122 days before Mistral Small 3.1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Small 3.1) vs 1M (Qwen2.5-Turbo (1M)). Mistral Small 3.1 is open weight, while Qwen2.5-Turbo (1M) is closed.

On HumanEval, Mistral Small 3.1 leads at 88.41% vs Qwen2.5-Turbo (1M) at 86.6%. On MATH, Qwen2.5-Turbo (1M) leads at 81.1% vs Mistral Small 3.1 at 69.3%. On MMLU-Pro, Mistral Small 3.1 leads at 66.76% vs Qwen2.5-Turbo (1M) at 64.5%.