Compare AI models

Specifications
Parameters
—4B/30B/235B
Context window
128k256k
Benchmarks
LiveCodeBench
75%74.1%
AIME 2025
83.48%92.3%
GPQA Diamond
76.26%81.1%
Overview
CompanyMistralQwen
Release dateSep 17 2025Jul 21 2025
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

Qwen3-2507 leads Magistral Medium 1.2 on 2 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Qwen3-2507 shipped 58 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Medium 1.2) vs 256k (Qwen3-2507). Magistral Medium 1.2 is closed, while Qwen3-2507 is open weight.

On LiveCodeBench, Magistral Medium 1.2 leads at 75% vs Qwen3-2507 at 74.1%. On AIME 2025, Qwen3-2507 leads at 92.3% vs Magistral Medium 1.2 at 83.48%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Magistral Medium 1.2 at 76.26%.