Nemotron 3 Nano Omni 30B A3B (Reasoning): benchmark results
Nemotron 3 Nano Omni 30B-A3B (Reasoning) supports video, audio, image and text input with text output, 256K context, and approximately 3B active parameters per generated token. The publisher describes a 31B hybrid MoE backbone; encoder processing adds modality-dependent work. Provider: NVIDIA. Released 2026-04-28. Access: Open.
Aggregate Rating 1508 ± 21, rank #1056 of 2170 rated models, from 35 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 63.2 | Accuracy (%) | 74.4 |
| AA Omniscience - Software Engineering (SWE) - Kotlin | 20 | Accuracy (%) | 63 |
| AA Omniscience - Software Engineering (SWE) - Rust | 50 | Accuracy (%) | 59 |
| AA Omniscience - Software Engineering (SWE) - Swift | 32 | Accuracy (%) | 51.2 |
| Tau2-Bench Telecom | 45.32 | Success Rate (%) | 50.6 |
| AA Omniscience - Software Engineering (SWE) - Java | 15 | Accuracy (%) | 49.8 |
| AA TAU-2 Bench | 45.32 | Accuracy (%) | 49.2 |
| AA Omniscience - Software Engineering (SWE) - Julia | 8 | Accuracy (%) | 46.1 |
| ParseBench - Semantic Formatting | 59.69 | Semantic Formatting Score | 43.3 |
| AA Terminal-Bench Hard | 8.33 | Accuracy (%) | 41.8 |
| ParseBench - Charts | 31.47 | ChartDataPointMatch Score | 40 |
| AA Omniscience - Software Engineering (SWE) - Dart | 14 | Accuracy (%) | 36.2 |
Interactive version: theaggregate.ai/model?slug=nemotron-3-nano-omni-30b-a3b-reasoning · How It Works · Data refreshed daily, snapshot 2026-11-05.