Compare AI models

Specifications
Parameters
671B—
Context window
128k2M
Benchmarks
LiveCodeBench
88.7%80%
AIME 2025
96%92%
GPQA Diamond
85.7%85.7%
Overview
CompanyDeepSeekSpaceXSI
Release dateDec 1 2025Sep 19 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

DeepSeek-V3.2-Speciale leads Grok 4 Fast on 2 of the 3 benchmarks they both report (LiveCodeBench, AIME 2025, GPQA Diamond). Grok 4 Fast shipped 73 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 (Grok 4 Fast). DeepSeek-V3.2-Speciale is open weight, while Grok 4 Fast is closed.

On LiveCodeBench, DeepSeek-V3.2-Speciale leads at 88.7% vs Grok 4 Fast at 80%. On AIME 2025, DeepSeek-V3.2-Speciale leads at 96% vs Grok 4 Fast at 92%. On GPQA Diamond, both models score 85.7%.