Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
Benchmarks
LiveCodeBench
65.9%75%
AIME 2024
79.8%91.82%
GPQA Diamond
71.5%76.26%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025Sep 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Magistral Medium 1.2 leads DeepSeek R1 on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2024, GPQA Diamond). DeepSeek R1 shipped 240 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 128k (Magistral Medium 1.2). DeepSeek R1 is open weight, while Magistral Medium 1.2 is closed.

On LiveCodeBench, Magistral Medium 1.2 leads at 75% vs DeepSeek R1 at 65.9%. On AIME 2024, Magistral Medium 1.2 leads at 91.82% vs DeepSeek R1 at 79.8%. On GPQA Diamond, Magistral Medium 1.2 leads at 76.26% vs DeepSeek R1 at 71.5%.