Compare AI models

Specifications
Parameters
236B24B
Context window
128k40k
Benchmarks
LiveCodeBench
39.7%55.84%
Overview
CompanyDeepSeekMistral
Release dateJul 24 2024Jun 10 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Small leads DeepSeek Coder V2-0724 on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek Coder V2-0724 shipped 321 days before Magistral Small, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2-0724 has 236B parameters, while Magistral Small has 24B. Context windows are 128k (DeepSeek Coder V2-0724) vs 40k (Magistral Small).

On LiveCodeBench, Magistral Small leads at 55.84% vs DeepSeek Coder V2-0724 at 39.7%.