Compare AI models

Specifications
Parameters
671B—
Context window
128k40k
Benchmarks
LiveCodeBench
65.9%59.36%
AIME 2024
79.8%73.59%
GPQA Diamond
71.5%70.83%
Overview
CompanyDeepSeekMistral
Release dateJan 20 2025Jun 10 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 leads Magistral Medium on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2024, GPQA Diamond). DeepSeek R1 shipped 141 days before Magistral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1) vs 40k (Magistral Medium). DeepSeek R1 is open weight, while Magistral Medium is closed.

On LiveCodeBench, DeepSeek R1 leads at 65.9% vs Magistral Medium at 59.36%. On AIME 2024, DeepSeek R1 leads at 79.8% vs Magistral Medium at 73.59%. On GPQA Diamond, DeepSeek R1 leads at 71.5% vs Magistral Medium at 70.83%.