Compare AI models

Specifications
Parameters
16B/236B—
Context window
128k40k
Benchmarks
LiveCodeBench
43.4%59.35%
Overview
CompanyDeepSeekMistral
Release dateJun 14 2024Jul 24 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Magistral Medium 1.1 leads DeepSeek Coder V2 on 1 of the 1 benchmark they both report (LiveCodeBench). DeepSeek Coder V2 shipped 405 days before Magistral Medium 1.1, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek Coder V2) vs 40k (Magistral Medium 1.1). DeepSeek Coder V2 is open weight, while Magistral Medium 1.1 is closed.

On LiveCodeBench, Magistral Medium 1.1 leads at 59.35% vs DeepSeek Coder V2 at 43.4%.