# NVIDIA Nemotron 3 Nano 30B A3B

As of October 21, 2026, NVIDIA Nemotron 3 Nano 30B A3B ranks #167 of 213 models overall with 8.9 on the Artificial Analysis Intelligence Index. Its strongest category is reasoning, where it ranks #127 of 203. NVIDIA Nemotron 3 Nano 30B A3B costs $0.06 per million input tokens and $0.24 per million output tokens. It was released on December 14, 2025.

Page: https://llmbenchmark.ai/models/nvidia-nemotron-3-nano-30b-a3b
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: NVIDIA
- Released: December 14, 2025
- Price per million input tokens: $0.06
- Price per million output tokens: $0.24
- Context window: 262K tokens
- Overall rank: 167 of 213, by the Artificial Analysis Intelligence Index
- Artificial Analysis Intelligence Index: 8.9

Benchmark results (42 of 190):

- AA Intelligence Index: 8.9 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Coding Index: 14.4 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Agentic Index: 1.0 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- AA Math Index: 91.0 (source: Artificial Analysis, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 75.7% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 11.4% (source: Artificial Analysis, read October 21, 2026)
- MMLU Pro (Artificial Analysis run): 79.4% (source: Artificial Analysis, read October 21, 2026)
- LiveCodeBench (Artificial Analysis run): 74.1% (source: Artificial Analysis, read October 21, 2026)
- SciCode: 30.6% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 13.6% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 71.1% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 38.0% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 40.9% (source: Artificial Analysis, read October 21, 2026)
- AIME 2025 (Artificial Analysis run): 91.0% (source: Artificial Analysis, read October 21, 2026)
- LMArena Text: 1348 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: coding: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts: 1348 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: math: 1371 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: instruction following: 1303 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: creative writing: 1269 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: English: 1377 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: non-English: 1320 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Chinese: 1383 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: German: 1348 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Japanese: 1268 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Korean: 1269 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: French: 1396 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Spanish: 1376 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Russian: 1304 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: Polish: 1303 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: multi-turn: 1319 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: longer queries: 1300 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: expert: 1355 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: hard prompts in English: 1376 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: software and IT: 1383 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: mathematical work: 1375 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: science: 1353 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: medicine and healthcare: 1349 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: legal and government: 1341 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: business and finance: 1346 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: writing and language: 1283 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)
- LMArena Text: entertainment and media: 1293 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)