NVIDIA, open weights
Nemotron 3 Nano 30B A3B
Nemotron 3 Nano 30B A3B by NVIDIA ranks 147th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.6. Its strongest category is reasoning, where it ranks 124th. API pricing starts at $0.05 per million input tokens and $0.20 per million output tokens, with a 262K-token context window.
Last verified
Specifications
- Noometry rank
- #147 of 354
- Index score
- 40.6
- Evidence
- Confirmed 18 results
- Provider
NVIDIA- Released
- December 15, 2025
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 262K
- Max output
- 262K
- Input price
- $0.05 / M
- Output price
- $0.20 / M
- Blended price
- $0.0875 / M
- Output speed
- Not measured
- Value
- #9 of 219
- Knowledge cutoff
- Unknown
- Input
- text
- Hugging Face
- nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
Category scores
Each category score combines every public result we have in that category.
- Coding 40.5
- Reasoning 27.1
- Math 37.8
- Knowledge 38.2
- Multilingual 45.8
- Instruction Following 68.8
- Long Context 39.5
- Writing & Preference 52.3
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 40.5 | #138 | 1 |
| Reasoning | 27.1 | #124 | 1 |
| Math | 37.8 | #147 | 1 |
| Knowledge | 38.2 | #148 | 2 |
| Multilingual | 45.8 | #162 | 1 |
| Instruction Following | 68.8 | #180 | 1 |
| Long Context | 39.5 | #175 | 1 |
| Writing & Preference | 52.3 | #174 | 3 |
Strengths and weaknesses
Categories where Nemotron 3 Nano 30B A3B places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Long Context | 39.5 | −1.4 | #175 of 296, top 60% |
| Instruction Following | 68.8 | −2.4 | #180 of 305, top 60% |
| Writing & Preference | 52.3 | −1.5 | #174 of 312, top 56% |
Closest competitors
The models ranked just above and below Nemotron 3 Nano 30B A3B. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| o1 | #143 | 40.9 | $26.25 | — | Compare |
| Gemini 3.1 Flash Lite | #144 | 40.8 | $0.56 | 10 | Compare |
| Claude Sonnet 4 | #145 | 40.8 | $6 | 31 | Compare |
| Qwen2.5-Max | #146 | 40.7 | — | — | Compare |
| Granite 4.2 8B | #148 | 40.5 | $0.11 | — | Compare |
| Step 3 | #149 | 40.5 | — | 7 | Compare |
| MiniMax M1 | #150 | 40.3 | $0.96 | — | Compare |
| Nvidia Llama 3.3 Nemotron Super 49b v1.5 | #151 | 40.3 | $0.40 | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Coding | 1378 | #152 of 294, top 52% | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Hard Prompts | 1348 | #162 of 297, top 55% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Math | 1371 | #149 of 285, top 53% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Vectara Hallucination Rate (lower is better) | 9.6% | #52 of 96, top 55% | Vectara Hallucination Leaderboard | ||
| LMArena Expert | 1355 | #154 of 273, top 57% | LMArena | 2026-10-08 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1320 | #162 of 297, top 55% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1382 | #149 of 285, top 53% | LMArena | 2026-10-08 | |
| LMArena French | 1396 | #124 of 223, top 56% | LMArena | 2026-10-08 | |
| LMArena German | 1348 | #133 of 231, top 58% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1268 | #134 of 211, top 64% | LMArena | 2026-10-08 | |
| LMArena Korean | 1269 | #141 of 213, top 67% | LMArena | 2026-10-08 | |
| LMArena Russian | 1303 | #176 of 283, top 63% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1376 | #129 of 226, top 58% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1304 | #176 of 298, top 60% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1300 | #188 of 291, top 65% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1348 | #160 of 297, top 54% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1269 | #190 of 295, top 65% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1319 | #176 of 295, top 60% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $0.06 | $0.24 | — | 2026-10-10 |
| deepinfra | $0.05 | $0.20 | $0.025 | 2026-10-10 |
| openrouter | $0.06 | $0.24 | — | 2026-10-10 |
Compare Nemotron 3 Nano 30B A3B
- Nemotron 3 Nano 30B A3B vs Qwen2.5-Max
- Nemotron 3 Nano 30B A3B vs Granite 4.2 8B
- Nemotron 3 Nano 30B A3B vs Claude Sonnet 4
- Nemotron 3 Nano 30B A3B vs Step 3
- Nemotron 3 Nano 30B A3B vs Gemini 3.1 Flash Lite
- Nemotron 3 Nano 30B A3B vs MiniMax M1
- Nemotron 3 Nano 30B A3B vs GPT-6 Astra
- Nemotron 3 Nano 30B A3B vs Claude Fable 5.1
- Nemotron 3 Nano 30B A3B vs Gemini 3.8 Flash
- Nemotron 3 Nano 30B A3B vs Kimi K3
- Nemotron 3 Nano 30B A3B vs Grok 4.6
- Nemotron 3 Nano 30B A3B vs Qwen3.8 Max
- Nemotron 3 Nano 30B A3B vs GLM-5.3
- Nemotron 3 Nano 30B A3B vs Muse Spark 1.3
Frequently asked questions
How good is Nemotron 3 Nano 30B A3B?
Nemotron 3 Nano 30B A3B by NVIDIA ranks 147th of 354 ranked models on the Noometry Index as of October 2026, with a score of 40.6. Its strongest category is reasoning, where it ranks 124th. API pricing starts at $0.05 per million input tokens and $0.20 per million output tokens, with a 262K-token context window.
How much does Nemotron 3 Nano 30B A3B cost?
Nemotron 3 Nano 30B A3B costs $0.05 per million input tokens and $0.20 per million output tokens on deepinfra, with cached input at $0.025.
What is Nemotron 3 Nano 30B A3B's context window?
Nemotron 3 Nano 30B A3B accepts up to 262K tokens of input and can write up to 262K tokens in one response.
Is Nemotron 3 Nano 30B A3B open source?
Yes. Nemotron 3 Nano 30B A3B's weights are downloadable from Hugging Face (nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16); check the license for commercial terms.
What are Nemotron 3 Nano 30B A3B's strengths and weaknesses?
Relative to other ranked models, Nemotron 3 Nano 30B A3B places best in reasoning, coding, math and lowest in long context, instruction following, writing & preference.
What is Nemotron 3 Nano 30B A3B best at?
Its best category is reasoning, where it ranks 124th on Noometry.