Compare AI models

Specifications
Parameters
—4B/30B/235B
Context window
128k256k
API pricing
Cheapest input
$0.44Mistral—
Cheapest output
$2.20Mistral—
$198Mistral—
Benchmarks
LiveCodeBench
30.3%74.1%
IFEval
89.4%87.8%
GPQA Diamond
57.1%81.1%
MMLU-Pro
77.2%84.4%
Overview
CompanyMistralQwen
Release dateMay 7 2025Jul 21 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Mistral Medium 3 on 3 of the 4 benchmarks they both report (LiveCodeBench, IFEval, GPQA Diamond, MMLU-Pro). Mistral Medium 3 shipped 75 days before Qwen3-2507, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Mistral Medium 3) vs 256k (Qwen3-2507). Mistral Medium 3 is closed, while Qwen3-2507 is open weight.

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Mistral Medium 3 at 30.3%. On IFEval, Mistral Medium 3 leads at 89.4% vs Qwen3-2507 at 87.8%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Mistral Medium 3 at 57.1%. On MMLU-Pro, Qwen3-2507 leads at 84.4% vs Mistral Medium 3 at 77.2%.