Compare AI models

Specifications
Parameters
671B—
Context window
128k128k
API pricing
Cheapest input
$0.50DeepInfra—
Cheapest output
$2.15DeepInfra—
$208DeepInfra · fp4—
Benchmarks
LiveCodeBench
73.3%75%
AIME 2024
91.4%91.82%
AIME 2025
87.5%83.48%
GPQA Diamond
81%76.26%
Overview
CompanyDeepSeekMistral
Release dateMay 28 2025Sep 17 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek R1-0528 and Magistral Medium 1.2 are evenly matched across the 4 benchmarks they both report (LiveCodeBench, AIME 2024, AIME 2025, GPQA Diamond). DeepSeek R1-0528 shipped 112 days before Magistral Medium 1.2, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek R1-0528) vs 128k (Magistral Medium 1.2). DeepSeek R1-0528 is open weight, while Magistral Medium 1.2 is closed.

On LiveCodeBench, Magistral Medium 1.2 leads at 75% vs DeepSeek R1-0528 at 73.3%. On AIME 2024, Magistral Medium 1.2 leads at 91.82% vs DeepSeek R1-0528 at 91.4%. On AIME 2025, DeepSeek R1-0528 leads at 87.5% vs Magistral Medium 1.2 at 83.48%. On GPQA Diamond, DeepSeek R1-0528 leads at 81% vs Magistral Medium 1.2 at 76.26%.