Skip to main content

Nemotron 3 Super 120B A12B (Reasoning)

NVIDIAOpen WeightNVIDIA Open Model License Agreement · Commercial OK

Description

Nemotron 3 Super is a 120B total / 12B active parameter hybrid Mamba-Attention Mixture-of-Experts model optimized for agentic reasoning, coding, planning, tool calling, and long-context analysis. It introduces LatentMoE (projecting tokens into a compressed latent space for expert routing, enabling 4x more experts at the same inference cost), Multi-Token Prediction for native speculative decoding (up to 3x faster generation), and native NVFP4 pretraining on Blackwell. The hybrid architecture interleaves Mamba-2 layers for linear-time sequence processing with strategically placed Transformer attention layers as global anchors, supporting a 1M-token context window. Pre-trained on 25 trillion tokens and post-trained with multi-environment RL across 21 configurations using NeMo Gym/RL with 1.2 million rollouts. Achieves up to 5x higher throughput than previous Nemotron Super and 2.2x higher throughput than GPT-OSS-120B while maintaining comparable accuracy.

Release Date
2026-03-11
Parameters
120.0B
Context Length
262K
Modalities
text

Capability Radar

60
general
50
coding
70
reasoning
51
scienceest.
50
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

Tau2 Airline56.3%SR
Multi-Challenge55.2%SR

Communication

Tau2 Telecom64.4%SR
Tau2 Retail62.8%SR

General

Arena-Hard v273.9%SR

Instruction Following

IFBench72.6%SR

Language

WMT24++86.7%SR
MMLU-Pro83.7%SR
MMLU-ProX79.4%SR

Long Context

RULER91.8%SR

Math

HMMT 202594.7%SR
AIME 202590.2%SR

Reasoning

GPQANYU + Cohere + Anthropic (2023)82.7%SR
LiveCodeBench81.2%SR
AA-LCR58.3%SR
SWE-Bench Verified53.7%SR
SWE-bench Multilingual45.8%SR
SciCode42.0%SR
Bird-SQL (dev)41.8%SR
BrowseCompOpenAI (2025)31.3%SR
Terminal-Bench 2.0Stanford × Laude Institute (2026)31.0%SR
Terminal-Bench25.8%SR
Humanity's Last Exam22.8%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
80
Legal
80
Long Context
80
Finance
80
Healthcare
80
Instruction Following
70
Math
70
Creativity
70
Writing
70
Chat
60
Physics
60
Reasoning
60
General
60
Biology
60
Chemistry
60
Communication
60
Frontend Development
50
Code
50
Tool Calling
50
Search
30
Agents
30
Vision
20

Pricing

Input Price$0.3 / 1M tokens
Output Price$0.9 / 1M tokens
Blended Price (3:1)$0.16375 / 1M tokens

Speed

Tokens/sec193.7
Time to First Token1.06s
Time to Answer11.38s

Provider Price Ranking

Provider Price Ranking

9 providers

Cheapest: NanoGPTMost Expensive: Nebius Token Factory
ProviderInputOutput
1NanoGPTCheapest
$0.05
$0.25
2Kilo Gateway
$0.06
$0.32
3OpenRouter
$0.075
$0.4
4DeepInfra
$0.085
$0.4
5Requesty
$0.1
$0.5
6Vercel AI Gateway
$0.15
$0.65
7Perplexity Agent
$0.25
$2.5
8NVIDIAPRIMARY
$0.3
$0.9
9Nebius Token Factory
$0.3
$0.9

Compare pricing across different API providers for this model.

External Sources