Compare AI models

Specifications
Parameters
671B—
Context window
128k40k
API pricing
Cheapest input
$0.256DeepInfra—
Cheapest output
$0.712DeepInfra—
$103StreamLake—
Benchmarks
LiveCodeBench
40.5%59.36%
GPQA Diamond
59.1%70.83%
Overview
CompanyDeepSeekMistral
Release dateDec 26 2024Jun 10 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Magistral Medium leads DeepSeek V3 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek V3 shipped 166 days before Magistral Medium, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3) vs 40k (Magistral Medium). DeepSeek V3 is open weight, while Magistral Medium is closed.

On LiveCodeBench, Magistral Medium leads at 59.36% vs DeepSeek V3 at 40.5%. On GPQA Diamond, Magistral Medium leads at 70.83% vs DeepSeek V3 at 59.1%.