Compare AI models

Specifications
Parameters
671B24B
Context window
128k128k
API pricing
Cheapest input
$0.2088GMICloud—
Cheapest output
$0.3096GMICloud—
$57.24GMICloud · fp8—
Benchmarks
LiveCodeBench
83.3%70.88%
AIME 2025
93.1%77.34%
GPQA Diamond
82.4%70.07%
Overview
CompanyDeepSeekMistral
Release dateDec 1 2025Sep 17 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2 leads Magistral Small 1.2 on 3 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Magistral Small 1.2 shipped 75 days before DeepSeek-V3.2, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2 has 671B parameters, while Magistral Small 1.2 has 24B. Context windows are 128k (DeepSeek-V3.2) vs 128k (Magistral Small 1.2).

On LiveCodeBench, DeepSeek-V3.2 leads at 83.3% vs Magistral Small 1.2 at 70.88%. On AIME 2025, DeepSeek-V3.2 leads at 93.1% vs Magistral Small 1.2 at 77.34%. On GPQA Diamond, DeepSeek-V3.2 leads at 82.4% vs Magistral Small 1.2 at 70.07%.