Private AI
Nvidia's Nemotron 3 Super 120B A12B model from the March 2026 Nemotron 3 release. It uses a hybrid Mamba-Transformer MoE architecture and targets agentic and coding workloads with a 262K context window here.
Added Mar 1, 2026
Model weightsContext Window
262.1K
Max Output
16.4K
Avg output tokens (7d)
1.3K tokens
Input Price (Auto)
$0.053/1M
Output Price (Auto)
$0.26/1M
Cache Read (Auto)
$0.026/1M
Capabilities
Performance metrics and benchmarks
Sourced from Artificial Analysis.
Intelligence Index
25.4
Choose explicit providers for this model. Auto routing remains available as the default option.
Loading provider options…
Coding Index
37.7
Agentic Index
8.7
GPQA Diamond
Graduate-level scientific reasoning
80.0%
Better than 72% of models compared
HLE
Humanity's Last Exam
19.2%
Better than 78% of models compared
IFBench
Instruction-following benchmark
71.5%
Better than 88% of models compared
T²-Bench Telecom
Conversational AI agents in dual-control scenarios
67.8%
Better than 61% of models compared
AA-LCR
Long context reasoning evaluation
60.0%
Better than 71% of models compared
GDPval-AA
Economically valuable tasks
9.9%
CritPt
Research-level physics reasoning
3.1%
SciCode
Python programming for scientific computing
36.0%
Better than 57% of models compared
Terminal-Bench Hard
Agentic coding and terminal use
28.8%
AA-Omniscience Accuracy
Proportion of correctly answered questions
24.0%
AA-Omniscience Hallucination Rate
Rate of incorrect answers among non-correct responses
87.0%
Last updated Aug 4, 2026
Artificial AnalysisBetter than 71% of models compared
