Nemotron 3 Super 120B A12B (Reasoning)
By NVIDIA · released 2026-03-11 (7 months) · snapshot 2026-10-24
- Intelligence index
- 12.80
- Cost to run the AA index
- $1319
- Price per 1M tokens (in / out)
- $0.30 / $0.90
- End-to-end time
- 16.1s
Is Nemotron 3 Super 120B A12B (Reasoning) on the Pareto frontier, and what beats it?
Off the frontier
No. GPT-6.1 Sol (Max) is at least as smart for the same money or less.
Next step up: Claude Opus 5.5 (High, Default Fallback), smarter but dearer.
| # | Model | Creator | Intelligence | Total cost | E2E total | Open | Released | Frontier |
|---|---|---|---|---|---|---|---|---|
| 1 | Nemotron 3 Super 120B A12B (Reasoning) | NVIDIA | 12.80 | $1319 | 16.1s | 2026-03-11 | ||
| 2 | GPT-6.1 Sol (Max) | OpenAI | 51.80 | $1082 | 220.5s | 2026-09-29 | Frontier | |
| 3 | Claude Opus 5.5 (High, Default Fallback) | Anthropic | 53.60 | $2172 | 33.8s | 2026-09-22 | Frontier |
Open in the picker Daily check URL: 200 on the frontier, 409 once beaten
Nemotron 3 Super 120B A12B (Reasoning) today
Intelligence: Artificial Analysis Intelligence Index. Cost: total cost to run that benchmark, so reasoning tokens count. API id: nvidia-nemotron-3-super-120b-a12b.
Compare head to head
Suggested: what beats it, its effort levels, and frontier models near its price.
- Nemotron 3 Super 120B A12B (Reasoning) vs GPT-6.1 Sol (Max)
- Nemotron 3 Super 120B A12B (Reasoning) vs Claude Opus 5.5 (High, Default Fallback)
- Nemotron 3 Super 120B A12B (Reasoning) vs GPT-6.1 Sol (High)
- Nemotron 3 Super 120B A12B (Reasoning) vs GPT-6.1 Sol (Xhigh)
- Nemotron 3 Super 120B A12B (Reasoning) vs Kimi K3.1 Pro
Compare Nemotron 3 Super 120B A12B (Reasoning) with measured models
What the Nemotron 3 Super 120B A12B release did to the frontier on 2026-03-11
None of its 1 effort levels reached the frontier at launch.
Closest miss: Nemotron 3 Super 120B A12B (Reasoning), 2.8 points below Gemini 3.1 Flash-Lite at 8.5× the cost.
Should you use Nemotron 3 Super 120B A12B (Reasoning)?
Should you use Nemotron 3 Super 120B A12B (Reasoning)?
Only when it fits your setup: GPT-6.1 Sol (Max) is at least as smart for the same money or less, so Nemotron 3 Super 120B A12B (Reasoning) is off the value frontier today.
What is better and cheaper than Nemotron 3 Super 120B A12B (Reasoning)?
GPT-6.1 Sol (Max) — at least as smart for the same money or less.
How much does Nemotron 3 Super 120B A12B (Reasoning) cost?
$0.30/$0.90 in/out per 1M tokens, and $1319 to run the full Artificial Analysis Intelligence Index, the honest all-in number for reasoning models.
Is Nemotron 3 Super 120B A12B (Reasoning) on the Pareto frontier?
No: GPT-6.1 Sol (Max) beats it on intelligence, cost, or both.
Frontier membership by axis pair
Other axis pairs where Nemotron 3 Super 120B A12B (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-super-120b-a12b · Markdown: /api/v1/models/nvidia-nemotron-3-super-120b-a12b?format=md · llms.txt · agent skill