Compare AI models

Specifications
Parameters
16B/236B24B
Context window
128k128k
Benchmarks
LiveCodeBench
43.4%70.88%
Overview
CompanyDeepSeekMistral
Release dateJun 14 2024Sep 17 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Magistral Small 1.2 leads DeepSeek Coder V2 on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek Coder V2 shipped 460 days before Magistral Small 1.2, so benchmark comparisons should account for the intervening progress.

DeepSeek Coder V2 has 16B/236B parameters, while Magistral Small 1.2 has 24B. Context windows are 128k (DeepSeek Coder V2) vs 128k (Magistral Small 1.2).

On LiveCodeBench, Magistral Small 1.2 leads at 70.88% vs DeepSeek Coder V2 at 43.4%.