Compare AI models

Specifications
Parameters
16B120B
Context window
8k1M
API pricing
Cheapest input
—$0.00Nvidia
Cheapest output
—$0.00Nvidia
—$33.00Io Net · nvfp4
Benchmarks
LiveCodeBench
14.3%88.22%
GPQA Diamond
35.2%89.52%
Overview
CompanyMoonshot AINVIDIA
Release dateFeb 22 2025Oct 15 2026
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Nemotron 3.5 Super VL leads Moonlight on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). Moonlight shipped 600 days before Nemotron 3.5 Super VL, so benchmark comparisons should account for the intervening progress.

Moonlight has 16B parameters, while Nemotron 3.5 Super VL has 120B. Context windows are 8k (Moonlight) vs 1M (Nemotron 3.5 Super VL).

On LiveCodeBench, Nemotron 3.5 Super VL leads at 88.22% vs Moonlight at 14.3%. On GPQA Diamond, Nemotron 3.5 Super VL leads at 89.52% vs Moonlight at 35.2%.