Compare AI models

Specifications
Parameters
24B4B/30B/235B
Context window
128k256k
Benchmarks
LiveCodeBench
70.88%74.1%
AIME 2025
77.34%92.3%
GPQA Diamond
70.07%81.1%
Overview
CompanyMistralQwen
Release dateSep 17 2025Jul 21 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

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

Magistral Small 1.2 has 24B parameters, while Qwen3-2507 has 4B/30B/235B. Context windows are 128k (Magistral Small 1.2) vs 256k (Qwen3-2507).

On LiveCodeBench, Qwen3-2507 leads at 74.1% vs Magistral Small 1.2 at 70.88%. On AIME 2025, Qwen3-2507 leads at 92.3% vs Magistral Small 1.2 at 77.34%. On GPQA Diamond, Qwen3-2507 leads at 81.1% vs Magistral Small 1.2 at 70.07%.