Compare AI models

Specifications
Parameters
24B—
Context window
128k256k
Benchmarks
LiveCodeBench
70.88%79%
AIME 2025
77.34%91.7%
GPQA Diamond
70.07%87.5%
Overview
CompanyMistralSpaceXSI
Release dateSep 17 2025Jul 9 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Grok 4 leads Magistral Small 1.2 on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Grok 4 shipped 70 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Magistral Small 1.2) vs 256k (Grok 4). Magistral Small 1.2 is open weight, while Grok 4 is closed.

On LiveCodeBench, Grok 4 leads at 79% vs Magistral Small 1.2 at 70.88%. On AIME 2025, Grok 4 leads at 91.7% vs Magistral Small 1.2 at 77.34%. On GPQA Diamond, Grok 4 leads at 87.5% vs Magistral Small 1.2 at 70.07%.