Model profile
Nemotron 3 Nano Omni 30B A3B
Evidence summary
Safety. Nemotron 3 Nano Omni 30B A3B has an estimated Safety rank of #141; its 90% source-sensitivity interval is #27–#316. Its behavior-only rank is #142; company governance moves the combined estimate to #141. Published Safety evidence spans 3 eval lineages and 5 of 7 components. Its strongest relative result is TAC (base_welfare_rate, #16 of 92); its weakest is kindbench v0.1.0 psychological safety ranking (identity_collapse, #10 of 10).
Freedom. Nemotron 3 Nano Omni 30B A3B has an estimated Freedom rank of #505; its 90% source-sensitivity interval is #225–#654. Published Freedom evidence spans 2 eval lineages and 1 of 1 components. Its strongest relative result is kindbench v0.1.0 psychological safety ranking (emotional_safety, #4 of 10); its weakest is SpeechMap model completion (complete_pct, #154 of 181).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗nemotron-3-nano-omni-30b-a3b
- NVIDIA ↗qc69jvmznzxy/nemotron-3-nano-omni-30b-a3b-reasoning
- OpenRouter ↗nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
- Official model catalog ↗Family-level model document · nvidia · first party
- Release source ↗curated outward evidence
Safety evals
Rank and direction are specific to the Safety portfolio. Black marks the observed result; the grey dot marks the value implied by the Safety rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #234 / 358 | ↓0.8565 | Source ↗official | |
| kindbench v0.1.0 psychological safety rankingemotional_safety | #7 / 10 | ↑79.9 | Source ↗official | |
| kindbench v0.1.0 psychological safety rankingidentity_collapse | #10 / 10 | ↑70 | Source ↗official | |
| kindbench v0.1.0 psychological safety rankingsycophancy_spine | #8 / 10 | ↑70 | Source ↗official | |
| kindbench v0.1.0 psychological safety rankingvalue_integrity | #10 / 10 | ↑70 | Source ↗official | |
| TACbase_welfare_rate | #16 / 92 | ↑36.54 | Source ↗self run |
Freedom evals
Rank and direction are specific to the Freedom portfolio. Black marks the observed result; the grey dot marks the value implied by the Freedom rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Source |
|---|---|---|---|---|
| kindbench v0.1.0 psychological safety rankingemotional_safety | #4 / 10 | ↓79.9 | Source ↗official | |
| SpeechMap model completioncomplete_pct | #154 / 181 | ↑35.7 | Source ↗official |