Compare AI models

Specifications
Parameters
671B120B
Context window
128k1M
API pricing
Cheapest input
—$0.00Nvidia
Cheapest output
—$0.00Nvidia
—$33.00Io Net · nvfp4
Benchmarks
SWE-Bench Verified
49.2%71.1%
LiveCodeBench
65.9%88.22%
GPQA Diamond
71.5%89.52%
Overview
CompanyDeepSeekNVIDIA
Release dateJan 20 2025Oct 15 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3.5 Super VL leads DeepSeek R1 on 3 of the 3 benchmarks they both report (SWE-Bench Verified, LiveCodeBench, GPQA Diamond). DeepSeek R1 shipped 633 days before Nemotron 3.5 Super VL, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Nemotron 3.5 Super VL has 120B. Context windows are 128k (DeepSeek R1) vs 1M (Nemotron 3.5 Super VL).

On SWE-Bench Verified, Nemotron 3.5 Super VL leads at 71.1% vs DeepSeek R1 at 49.2%. On LiveCodeBench, Nemotron 3.5 Super VL leads at 88.22% vs DeepSeek R1 at 65.9%. On GPQA Diamond, Nemotron 3.5 Super VL leads at 89.52% vs DeepSeek R1 at 71.5%.