Compare AI models

Specifications
Parameters
24B—
Context window
256k—
Benchmarks
SWE-Bench Multilingual
55.7%56.9%
Terminal-Bench 2.0
22.5%40%
Overview
CompanyMistralSpaceXSI
Release dateDec 9 2025Oct 29 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Composer leads Devstral Small 2 (24B) on 2 of the 2 benchmarks they both report (SWE-Bench Multilingual, Terminal-Bench 2.0). Composer shipped 41 days before Devstral Small 2 (24B), so benchmark comparisons should account for the intervening progress.

Devstral Small 2 (24B) is open weight, while Composer is closed.

On SWE-Bench Multilingual, Composer leads at 56.9% vs Devstral Small 2 (24B) at 55.7%. On Terminal-Bench 2.0, Composer leads at 40% vs Devstral Small 2 (24B) at 22.5%.