Compare AI models

Specifications
Parameters
671B—
Context window
128k2M
Benchmarks
LiveCodeBench
88.7%36%
GPQA Diamond
85.7%64.7%
Overview
CompanyDeepSeekGoogle
Release dateDec 1 2025Feb 5 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2-Speciale leads Gemini 2.0 Pro on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Gemini 2.0 Pro shipped 299 days before DeepSeek-V3.2-Speciale, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (DeepSeek-V3.2-Speciale) vs 2M (Gemini 2.0 Pro). DeepSeek-V3.2-Speciale is open weight, while Gemini 2.0 Pro is closed.

On LiveCodeBench, DeepSeek-V3.2-Speciale leads at 88.7% vs Gemini 2.0 Pro at 36%. On GPQA Diamond, DeepSeek-V3.2-Speciale leads at 85.7% vs Gemini 2.0 Pro at 64.7%.