Skip to main content

NVIDIA Nemotron 3 Nano 30B-A3B BF16 vs NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4

SpecNVIDIA Nemotron 3 Nano 30B-A3B BF16NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
Respan Index15.6 (#157)28.4 (#96)
Blended price per 1M$0.088$0.925
Context window1M1M
Input / output per 1M$0.05 / $0.2$0.5 / $2.2
Max output--
Inputtexttext
Released2025-12-152026-06-04

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryNVIDIA Nemotron 3 Nano 30B-A3B BF16NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
Coding3.5* NVIDIA Nemotron 3 Nano 30B-A3B BF166.3 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
Agents13.1* NVIDIA Nemotron 3 Nano 30B-A3B BF1632.9 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
Reasoning21.0 NVIDIA Nemotron 3 Nano 30B-A3B BF1630.8 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
Knowledge & language10.3 NVIDIA Nemotron 3 Nano 30B-A3B BF1635.2 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
Human preference34.4 NVIDIA Nemotron 3 Nano 30B-A3B BF1649.5 NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 leads on 2 of the 2 benchmarks both report. Higher is better. Each score links to where it was published.

FAQ

Is NVIDIA Nemotron 3 Nano 30B-A3B BF16 better than NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4?

NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 scores 28.4 on the Respan Index (#96), ahead of NVIDIA Nemotron 3 Nano 30B-A3B BF16 at 15.6 (#157). NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 leads on 2 of the 2 benchmarks both report.

Which is cheaper, NVIDIA Nemotron 3 Nano 30B-A3B BF16 or NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4?

NVIDIA Nemotron 3 Nano 30B-A3B BF16 lists at $0.05 input and $0.2 output per 1M tokens; NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 at $0.5 and $2.2. NVIDIA Nemotron 3 Nano 30B-A3B BF16 is 11x cheaper per token at list price.

Which has the larger context window?

Both accept 1M tokens of context.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.