NVIDIA
NVIDIA Nemotron 3 Super 120B A12B (Reasoning)
NVIDIA Nemotron 3 Super 120B A12B (Reasoning) is a NVIDIA language-model profile in the Easy Benchmarks snapshot. Use this page to compare its measured Artificial Analysis scores, output speed, time to first token, pricing, and relative ranking against other models in the local catalog.
NVIDIA model catalogOperational Metrics
Output Speed162.5 tok/s
First Token1.00s
Blended Price$0.412/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseMar 11, 2026
Context Windown/a
Modalitiesn/a
Strength: Speed
Rank #44 across 293 models.
162.5 tok/s
Strength: HLE
Rank #72 across 474 models.
19.2%
Strength: Value
Rank #59 across 323 models.
87.4
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.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 36.0 | #101 |
| Artificial Analysis Coding Index | coding | 31.2 | #107 |
| GPQA | reasoning | 80.0% | #100 |
| Humanity's Last Exam | reasoning | 19.2% | #72 |
| SciCode |