NVIDIA
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
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. It delivers up to 7x higher throughput, providing fast, cost-efficient inference for agentic tasks. Additionally, a long context window gives the model long-term memory, preventing AI agents from losing focus on long, multi-step tasks and ensuring high-accuracy results. Fully open with weights, datasets, and recipes, Super allows easy customization and secure deployment anywhere.
NVIDIA model catalogModel Snapshot
TypeLanguage
ReleaseMar 11, 2026
Context262,144
Tagsreasoning, tool-use
Overall
Rank #199 across 600
25.4
Coding
Rank #147 across 266
37.7
Blended Price
Rank #93 across 379
$0.350/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed145.8 tok/s
First Token1.07s
Max Output16,384
Pricing
Blended$0.350/M
Input$0.200/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 25.4 | #199 |
| Artificial Analysis Coding Index | coding | 37.7 | #147 |
| GPQA | reasoning | 80.0% | #156 |
| Humanity's Last Exam | reasoning | 19.2% | #121 |
| SciCode |