Compare AI models

Specifications
Parameters
671B24B
Context window
128k40k
API pricing
Cheapest input
$0.27SiliconFlow—
Cheapest output
$0.41SiliconFlow—
$74.50SiliconFlow · fp8—
Benchmarks
LiveCodeBench
74.1%59.17%
AIME 2025
89.3%62.03%
GPQA Diamond
79.9%65.78%
Overview
CompanyDeepSeekMistral
Release dateSep 29 2025Jul 24 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

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

DeepSeek V3.2 Exp has 671B parameters, while Magistral Small 1.1 has 24B. Context windows are 128k (DeepSeek V3.2 Exp) vs 40k (Magistral Small 1.1).

On LiveCodeBench, DeepSeek V3.2 Exp leads at 74.1% vs Magistral Small 1.1 at 59.17%. On AIME 2025, DeepSeek V3.2 Exp leads at 89.3% vs Magistral Small 1.1 at 62.03%. On GPQA Diamond, DeepSeek V3.2 Exp leads at 79.9% vs Magistral Small 1.1 at 65.78%.