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...
Thinking
Knowledge Cutoff
2026-02-01
The date this AI finished learning. It may not know about things that happened after this date.
Input → Output Format
The types of content this AI can receive, and what it can produce in return.
Context Memory
262KIN1MOUT
The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.
Cost/1M Words
$0.1IN$0.5OUT
The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).
Calculate CostSource:Official Docs
AI Performance Evaluation
Overall
AA Intelligence Index
36%↓2%
Reasoning & Math
GPQA Diamond
80%↓1%
HLE
19%↑3%
Coding
AA Coding Index
31%↓3%
TAU2
68%↓4%
TerminalBench
29%↓2%
SciCode
36%↓5%
Language & Instructions
IFBench
72%↑16%
AA-LCR
60%↓2%
Output Speed
Standard Mode
80tok/s↑0
First Output 1.88s
Reasoning Mode
163tok/s↑46
First Output 13.16s