Quality
#34/6714.2
Overall quality score
🇺🇸NVIDIAOpen sourceNVIDIA: Nemotron 3 Nano 30B A3B.
See how NVIDIA: Nemotron 3 Nano 30B A3B compares with other broadly useful AI models across quality, speed, price, context, and practical capabilities.
Speed
#2/67189 t/s
Output tokens per second
Input price
#4/67$0.05/1M
Per 1M tokens
Output price
#8/67$0.20/1M
Per 1M tokens
Context
#39/67262.1K
Content read at once
Comparison summary
NVIDIA: Nemotron 3 Nano 30B A3B ranks #34 of 67 for overall quality and #2 for response speed in the current catalogue.
Its listed input price is $0.05/1M, output price is $0.20/1M, and it can work with up to 262.1K of context at once.
Its strongest areas in the current data are coding, everyday help, math and logic.
Practical specifications
- Company
- NVIDIA
- Reasoning
- Yes
- Open weights
- Yes
- Input
- Text
- Output
- Text
- Context window
- 262.1K
NVIDIA: Nemotron 3 Nano 30B A3B technical benchmarks.
Named evaluation records for technical comparison. Results retain their original benchmark names and sources.
| Benchmark | Area | Nemotron 3 Nano 30B A3B | Source |
|---|---|---|---|
| Intelligence Index | overallQuality | 14.2 | OpenRouter / artificial-analysis |
| Coding Index | coding | 14.4 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 2 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 75.7 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 10.2 | OpenRouter model benchmarks |
| IFBench | IFBench | 71.1 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 40.9 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 33.7 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 0 | OpenRouter model benchmarks |
| CritPt | CritPt | 0.9 | OpenRouter model benchmarks |
| SciCode | SciCode | 29.6 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 13.6 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 17.1 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 17.1 | OpenRouter model benchmarks |
| MMLU-Pro | Knowledge and reasoning | 78.3 | OpenEvals/leaderboard-data |
Quality benchmarks
See where NVIDIA: Nemotron 3 Nano 30B A3B stands.
The darker bar marks NVIDIA: Nemotron 3 Nano 30B A3B; the lighter bars provide context from other leading models.
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better