Compare AI models

Specifications
Parameters
671B32B
Context window
128k32k
Benchmarks
LiveCodeBench
88.7%50%
Overview
CompanyDeepSeekQwen
Release dateDec 1 2025Nov 28 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2-Speciale leads QwQ-32B-Preview on 1 of the 1 benchmark they both report (LiveCodeBench). QwQ-32B-Preview shipped 368 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2-Speciale has 671B parameters, while QwQ-32B-Preview has 32B. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 32k (QwQ-32B-Preview).

On LiveCodeBench, DeepSeek-V3.2-Speciale leads at 88.7% vs QwQ-32B-Preview at 50%.