Compare AI models

Specifications
Parameters
671B—
Context window
128k40k
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
Benchmarks
LiveCodeBench
74.1%59.35%
AIME 2025
89.3%60.99%
GPQA Diamond
79.9%71.46%
Overview
CompanyDeepSeekMistral
Release dateSep 29 2025Jul 24 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek V3.2 Exp leads Magistral Medium 1.1 on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Magistral Medium 1.1 shipped 67 days before DeepSeek V3.2 Exp, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek V3.2 Exp) vs 40k (Magistral Medium 1.1). DeepSeek V3.2 Exp is open weight, while Magistral Medium 1.1 is closed.

On LiveCodeBench, DeepSeek V3.2 Exp leads at 74.1% vs Magistral Medium 1.1 at 59.35%. On AIME 2025, DeepSeek V3.2 Exp leads at 89.3% vs Magistral Medium 1.1 at 60.99%. On GPQA Diamond, DeepSeek V3.2 Exp leads at 79.9% vs Magistral Medium 1.1 at 71.46%.