Nemotron 3 Super 120B A12B (Reasoning): benchmark results
Provider: NVIDIA. Released 2026-03-11.
Aggregate Rating 1586 ± 14, rank #800 of 2245 rated models, from 86 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| K2 Horizon MoVA Card - CritPt | 3.1 | Score (%) | 91.7 |
| AA Omniscience - Software Engineering (SWE) - Julia | 32 | Accuracy (%) | 90.1 |
| AA IFBench | 71.5 | Accuracy (%) | 87.9 |
| AA Omniscience - Software Engineering (SWE) - TypeScript | 37.78 | Accuracy (%) | 84 |
| K2 Horizon MoVA Card - AA-Omniscience Accuracy | 24.3 | Score (%) | 83.3 |
| AA Omniscience - Software Engineering (SWE) - Swift | 48 | Accuracy (%) | 82.4 |
| AA Omniscience - Software Engineering (SWE) - JavaScript | 40 | Accuracy (%) | 81.6 |
| AA Omniscience - Software Engineering (SWE) - HTML | 44 | Accuracy (%) | 80.7 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 28 | Accuracy (%) | 80.5 |
| MT-JailBench - XTeaming | 37.74 | Attack success rate (%) of the XTeaming multi-turn jailbreak | 80 |
| AA Omniscience - Software Engineering (SWE) - PHP | 34 | Accuracy (%) | 79.4 |
| AA Omniscience - Software Engineering (SWE) - Dart | 26 | Accuracy (%) | 77.6 |
Interactive version: theaggregate.ai/model?slug=nemotron-3-super-120b-a12b-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-16.