NVIDIA AI & NIMopen-weight
Released: 2025-12-15Artificial AnalysisNemotron 3 Nano 30B A3B
NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully...
Intelligence Index
—/ 100
Artificial Analysis Intelligence Index (independent composite)Throughput Speed
170tok/sec
Output streaming throughputTime to First Answer
864ms
Time to first answer token, including any thinkingCost to Run the Index
—USD
Artificial Analysis cost of the full Index runMeasured results · Artificial Analysis
Independent evaluations of Nemotron 3 Nano 30B A3B (Non-reasoning configuration). Values are reported as published; nothing here is estimated or derived. Snapshot 2026-11-15.
- Intelligence Index
- —
- Cost to run the Index
- —
- Time per task
- —
- Omniscience index
- —
- Reasoning model
- No
- Cached-input price
- $0.05 / 1M
Reasoning & knowledge
- AIME 202513.3%
- CritPt0.0%
- GPQA Diamond39.9%
- Humanity's Last Exam4.6%
- IFBench37.5%
Coding & terminal agents
- LiveCodeBench36.0%
- Terminal-Bench Hard12.1%
Agentic work
- GDPval-AA (normalized Elo)-349 Elo
- τ²-Bench Telecom25.4%
Long context & documents
Reasoning-effort variants evaluated
| Variant | Intelligence Index | Cost to run Index | Output speed (tok/s) |
|---|---|---|---|
| Non-reasoning | — | — | 169.8 |
| Reasoning | — | — | 195.1 |
Headline Evaluation Breakdown
Six independently measured evaluations (Artificial Analysis)Math · AIME 202513.3%
Long context · AA-LCR10.7%
Knowledge · Humanity's Last Exam4.6%
Instruction following · IFBench37.5%
Sourced Benchmark Evaluations (9)
Verified performance across authoritative benchmarks with provenance tracking.| Benchmark | Status | Score | Trust | Date | Source Type | Provenance |
|---|---|---|---|---|---|---|
| AIME | Nearing Saturation | 13.3% | 75 | 2026-11-15 | independent | Source ↗ |
| GPQA | Nearing Saturation | 39.9% | 78 | 2026-11-15 | independent | Source ↗ |
| Humanity's Last Exam | Active | 4.6% | 93 | 2026-11-15 | independent | Source ↗ |
| LiveCodeBench | Saturated | 36% | 39 | 2026-11-15 | independent | Source ↗ |
| IFBench | Active | 37.5% | 93 | 2026-11-15 | independent | Source ↗ |
| τ²-Bench Telecom | Active | 25.4% | 93 | 2026-11-15 | independent | Source ↗ |
| Terminal-Bench Hard | Active | 12.1% | 93 | 2026-11-15 | independent | Source ↗ |
| AA-LCR (Long Context Reasoning) | Active | 10.7% | 93 | 2026-11-15 | independent | Source ↗ |
| CritPt | Active | 0% | 93 | 2026-11-15 | independent | Source ↗ |
Local Hardware Execution (Ollama)Hardware Compatible
# 1. Pull and execute model locally with Ollama
ollama run nvidia-nemotron-3-nano-30b-a3b
# 2. Or invoke via local OpenAI-compatible endpoint
curl http://localhost:11434/v1/chat/completions \
-H "Content-Type: application/json" \
-d '{
"model": "nvidia-nemotron-3-nano-30b-a3b",
"messages": [{"role": "user", "content": "Analyze reasoning chains on AIME 2026"}]
}'Evaluation & Sourcing Notes
Scores listed for Nemotron 3 Nano 30B A3B represent verified evaluations extracted from official research papers, independent evaluation suites (HELM, LMSYS, OpenCompass, LiveBench), and verified audit reports.
All benchmarks marked as saturated or deprecated reflect historical performance where the benchmark no longer provides active discriminative power.