Model profile
Nemotron 3 Nano 30B A3B
NVIDIAdeveloper
2025-12-15release date
#156 / 267overall rank
5eval lineages
1discovery sources
Evidence summary
Nemotron 3 Nano 30B A3B has an estimated overall rank of #156; its 90% source-sensitivity interval is #25–#240. Its behavior-only rank is #157; company governance moves the combined estimate to #156. Published evidence spans 5 evals and 4 of 7 behavior components. Its strongest relative result is TAC (base_welfare_rate, #22 of 68); its weakest is SM-Bench (anti_hallucination, #68 of 73).
Compare this model
Only models sharing at least one published sub-eval are listed.
Official and reference links
- Artificial Analysis ↗nvidia-nemotron-3-nano-30b-a3b
- NVIDIA ↗qc69jvmznzxy/nemotron-3-nano-30b-a3b
- OpenRouter ↗nvidia/nemotron-3-nano-30b-a3b
- Official model catalog ↗Family-level model document · nvidia · first party
- Release source ↗curated outward evidence
Published eval results
Rank is within that sub-eval. Black marks the observed result; the grey dot marks the value implied by the global rank. Values stay on each source’s native scale.
| Eval / sub-eval | Rank | Value | Distribution | Better | Source |
|---|---|---|---|---|---|
| AA-Omnisciencehallucination_rate | #177 / 311 | 0.8295 | ↓ lower | Source ↗official | |
| BullshitBench v2clear_pushback_rate | #67 / 105 | 0.19 | ↑ higher | Source ↗official | |
| Cisco AI Defense Rolling Single-Turn Leaderboardsingle_turn_attack_success_rate | #63 / 105 | 49.1 | ↓ lower | Source ↗official | |
| SM-Benchadversarial | #64 / 73 | 73.66 | ↑ higher | Source ↗official | |
| SM-Benchambiguous_interpretation | #63 / 73 | 71.43 | ↑ higher | Source ↗official | |
| SM-Benchanti_hallucination | #68 / 73 | 75.13 | ↑ higher | Source ↗official | |
| SM-Bencheq_boundaries | #60 / 73 | 53.93 | ↑ higher | Source ↗official | |
| SM-Benchoverfit | #60 / 73 | 42.62 | ↑ higher | Source ↗official | |
| TACbase_welfare_rate | #22 / 68 | 32.05 | ↑ higher | Source ↗self run |