Venice Atlas
← Back to model catalog

VENICE ATLAS · MODEL DOSSIER · NVIDIA NEMOTRON 3 NANO 30B

Model overview

NVIDIA Nemotron 3 Nano 30B

NVIDIA Nemotron 3 Nano 30B is a compact and efficient language model from NVIDIA, optimized for fast inference while maintaining strong performance across diverse tasks.

nvidia-nemotron-3-nano-30b-a3b · venice.ai
Text · Venice catalog$0.07 per 1M tokensPrice on Venice AI
ModalityTextOn Venice AI
Primary price$0.07 per 1M tokensper 1M tokens
Context window128KMax tokens
Benchmarks15Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Creativity#313.39 ratingWriting#313.39 rating
Chat2 results
Multi-Challengemultichallenge · chat
38.5%
ReportedOct 2026
Tau2 Airlinetau2-airline · chat
48.0%
ReportedOct 2026
Communication2 results
Tau2 Retailtau2-retail · communication
56.9%
ReportedOct 2026
Tau2 Telecomtau2-telecom · communication
42.2%
ReportedOct 2026
General intelligence1 result
Arena-Hard v2arena-hard-v2 · general
67.7%
ReportedOct 2026
Language3 results
MMLU-Prommlu-pro · language
78.3%
ReportedOct 2026
MMLU-ProXmmlu-prox · language
59.5%
ReportedOct 2026
WMT24++wmt24++ · language
86.2%
ReportedOct 2026
Math1 result
AIME 2025aime-2025 · math
99.2%
ReportedOct 2026
Reasoning6 results
GPQAgpqa · reasoning
75.0%
ReportedOct 2026
Humanity's Last Examhumanity's-last-exam · reasoning
15.5%
ReportedOct 2026
LiveCodeBench v6livecodebench-v6 · reasoning
68.3%
ReportedOct 2026
SciCodescicode · reasoning
33.3%
ReportedOct 2026
SWE-Bench Verifiedswe-bench-verified · reasoning
38.8%
ReportedOct 2026
Terminal-Benchterminal-bench · reasoning
8.50%
ReportedOct 2026

Learn what each benchmark measures ↗

Related models

More from nvidia

nvidia-nemotron-3-ultra-550b-a55bNVIDIA Nemotron 3 Ultra$0.63 input per 1M tokens ↗nvidia-nemotron-3-5-super-vl-120b-a12bNVIDIA Nemotron 3.5 Super VL 120B$0.25 input per 1M tokens ↗