AI Comparison
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...
Author
NVIDIARelease Date
2026-03-11
Knowledge Cutoff
2026-02-01
License
Proprietary
I/O Format
Context Length
262K / 1M
API I/O (1M)
$0.1 / $0.5
How to Use
—
Output Speed
80 tok/sArena Overall
—Intelligence Index
36.0Coding Index
31.2Math Index
—LiveBench
—ForecastBench
—GPQA Diamond
80.0%HLE
19.2%MMLU-Pro
—AIME 2025
—MATH-500
—LB Reasoning
—LB Math
—LB Data Analysis
—LiveCodeBench
—LB Coding
—LB Agentic
—TAU2
67.8%TerminalBench
28.8%SciCode
36.0%IFBench
71.5%AA-LCR
0.6Hallucination (HHEM)
—Factual Consistency (HHEM)
—LB Language
—LB Instruction Following
—1 / 3
좌우로 스와이프하여 전환
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...
Author
NVIDIARelease Date
2026-03-11
Knowledge Cutoff
2026-02-01
License
Proprietary
I/O Format
Context Length
262K / 1M
API I/O (1M)
$0.1 / $0.5
How to Use
—
Output Speed
80 tok/sArena Overall
—Intelligence Index
36.0Coding Index
31.2Math Index
—LiveBench
—ForecastBench
—GPQA Diamond
80.0%HLE
19.2%MMLU-Pro
—AIME 2025
—MATH-500
—LB Reasoning
—LB Math
—LB Data Analysis
—LiveCodeBench
—LB Coding
—LB Agentic
—TAU2
67.8%TerminalBench
28.8%SciCode
36.0%IFBench
71.5%AA-LCR
0.6Hallucination (HHEM)
—Factual Consistency (HHEM)
—LB Language
—LB Instruction Following
—