Compare AI models

Specifications
Parameters
24B—
Context window
40k1M
Benchmarks
LiveCodeBench
55.84%37.8%
Overview
CompanyMistralQwen
Release dateJun 10 2025Nov 15 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Magistral Small leads Qwen2.5-Turbo (1M) on 1 of the 1 benchmark they both report (LiveCodeBench). Qwen2.5-Turbo (1M) shipped 207 days before Magistral Small, so benchmark comparisons should account for the intervening progress.

Context windows are 40k (Magistral Small) vs 1M (Qwen2.5-Turbo (1M)). Magistral Small is open weight, while Qwen2.5-Turbo (1M) is closed.

On LiveCodeBench, Magistral Small leads at 55.84% vs Qwen2.5-Turbo (1M) at 37.8%.