NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)
By NVIDIA · released 2025-12-15 (10 months) · snapshot 2026-10-24
- Intelligence index
- 8.90
- Cost to run the AA index
- $63.7
- Price per 1M tokens (in / out)
- $0.05 / $0.20
- End-to-end time
- 11.6s
Is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) on the Pareto frontier, and what beats it?
Off the frontier
No. Claude Haiku 5.5 (Medium) is at least as smart for the same money or less.
Next step up: GPT-6 Luna (Xhigh), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | NVIDIA | 8.90 | $63.7 | 11.6s | 2025-12-15 | ||
| 2 | Claude Haiku 5.5 (Medium) | Anthropic | 34.50 | $56.4 | 10.4s | 2026-10-07 | Frontier | |
| 3 | GPT-6 Luna (Xhigh) | OpenAI | 34.60 | $66.8 | 21.3s | 2026-09-22 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) today
1 of 2 effort levels plotted. The remaining levels lack intelligence or benchmark cost data.
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: nvidia-nemotron-3-nano-30b-a3b-reasoning.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs Claude Haiku 5.5 (Medium)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs GPT-6 Luna (Xhigh)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs GPT-6 Luna (Medium)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs GPT-6 Luna (High)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs Claude Haiku 5.5 (High)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs MiMo-V2.6-Flash
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs GPT-6 Luna (Max)
- NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) vs Claude Haiku 5.5 (Xhigh)
Compare NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) with measured models
What the NVIDIA Nemotron 3 Nano 30B A3B release did to the frontier on 2025-12-15
None of its 2 effort levels reached the frontier at launch.
Closest miss: NVIDIA Nemotron 3 Nano 30B A3B (Reasoning), 0.8 points below DeepSeek V3 0324 at 3.2× the cost.
Should you use NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
Should you use NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
Only when it fits your setup: Claude Haiku 5.5 (Medium) is at least as smart for the same money or less, so NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is off the value frontier today.
What is better and cheaper than NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)?
Claude Haiku 5.5 (Medium) — at least as smart for the same money or less.
How much does NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) cost?
$0.05/$0.20 in/out per 1M tokens, and $63.7 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) on the Pareto frontier?
No: Claude Haiku 5.5 (Medium) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) is Pareto-optimal.
| Y axis | X axis | On the frontier |
|---|---|---|
| AA intelligence index | AA total cost to run (USD) | |
| AA intelligence index | End-to-end total seconds | |
| AA intelligence index | Output speed tokens/sec |
Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/models/nvidia-nemotron-3-nano-30b-a3b-reasoning · Markdown: /api/v1/models/nvidia-nemotron-3-nano-30b-a3b-reasoning?format=md · llms.txt · agent skill