Compare AI models

Specifications
Parameters
671B—
Context window
128k200k
Benchmarks
GPQA Diamond
85.7%81.3%
Overview
CompanyDeepSeekOpenAI
Release dateDec 1 2025Apr 16 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2-Speciale leads o4-mini-high on 1 of the 1 benchmark they both report (GPQA Diamond). o4-mini-high shipped 229 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek-V3.2-Speciale) vs 200k (o4-mini-high). DeepSeek-V3.2-Speciale is open weight, while o4-mini-high is closed.

On GPQA Diamond, DeepSeek-V3.2-Speciale leads at 85.7% vs o4-mini-high at 81.3%.