NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. Built on a hybrid Mamba-Transformer...
Tested on 18 benchmarks · BenchGecko score 10.2. Top scores: Artificial Analysis · GPQA Diamond (80.0%), Artificial Analysis · IFBench (71.5%), Artificial Analysis · tau2-Bench Telecom (67.8%).
Llama 3.2 1B Instruct scores 11.7 (115% as good) at $0.03/1M input · 66% cheaper
Regularly refreshed coding problems that avoid data contamination. New problems added monthly to prevent memorization.
LiveBench coding tasks that require multi-step reasoning and tool use. Tests planning and execution of complex coding workflows.
Regularly refreshed reasoning problems testing logical deduction, spatial reasoning, and analytical thinking.
Fresh data analysis tasks testing ability to interpret tables, charts, and statistical data.
Regularly updated math problems that test numerical reasoning, algebra, calculus, and combinatorics.
- Typetext
- Context262K tokens (~131 books)
- ReleasedMar 2026
- LicenseOpen Source
- StatusActive
- Cost / Message~$0.001
Frequently Asked Questions
Related Models
Gemma 3 12B · Google DeepMindPythia 160m · eleutheraiQwen2 0.5B · AlibabaSmolLM2 135M · Hugging Face TBGpt2 Medium · OpenAIKey facts · as of 2026-10-05
- Nemotron 3 Super by NVIDIA. BenchGecko score 10.2, rank 299 of 312 scored models (normalized average of public benchmark scores).
- List price $0.0800 input · $0.45 output per 1M tokens (as of 2026-10-05).
- Sold by 2 providers (as of 2026-10-05): DekaLLM (fp8) $0.0800 in / $0.45 out · DeepInfra (bf16) $0.0850 in / $0.40 out. Every provider
How to cite · data as of 2026-10-05
Nemotron 3 Super · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/nemotron-3-super-120b-a12b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP