Compare AI models

Specifications
Parameters
671B74B
Context window
128k256k
Benchmarks
GPQA Diamond
85.7%86.43%
Overview
CompanyDeepSeekNVIDIA
Release dateDec 1 2025Oct 15 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3.5 Bolt 74B leads DeepSeek-V3.2-Speciale on 1 of the 1 benchmark they both report (GPQA Diamond). DeepSeek-V3.2-Speciale shipped 318 days before Nemotron 3.5 Bolt 74B, so benchmark comparisons should account for the intervening progress.

DeepSeek-V3.2-Speciale has 671B parameters, while Nemotron 3.5 Bolt 74B has 74B. Context windows are 128k (DeepSeek-V3.2-Speciale) vs 256k (Nemotron 3.5 Bolt 74B).

On GPQA Diamond, Nemotron 3.5 Bolt 74B leads at 86.43% vs DeepSeek-V3.2-Speciale at 85.7%.