Compare / head-to-head
NVIDIA Nemotron 3 Nano 30B-A3B BF16vsNVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 leads 2 of 2 shared benchmarks. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 2
NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 leads
Cheaper per token
—
list price, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
100%
NVIDIA
NVIDIA Nemotron 3 Nano 30B-A3B BF16
NVIDIA · released 2025-12-15
text
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 10 · 9 core
NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4
NVIDIA · released 2026-06-04
text
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 4 core
Quality
Benchmark matrix
2 shared · 8 only NVIDIA Nemotron 3 Nano 30B-A3B BF16 · 4 only NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4| Benchmark | NVIDIA Nemotron 3 Nano 30B-A3B BF16 | NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 2 | ||||
| Humanity's Last Exam (no tools) | 10.6% ↗ | 26.1% ↗ | -15.5 pt | NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
| LMArena Elo | 1348.4 ↗ | 1444.7 ↗ | -96.3 | NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 |
| Only NVIDIA Nemotron 3 Nano 30B-A3B BF16 reports · 8 | ||||
| MMLU-Pro | 78.3% ↗ | not reported | — | — |
| AIME 2025 | 89.1% ↗ | not reported | — | — |
| AIME 2025 (with tools) | 99.2% ↗ | not reported | — | — |
| GPQA (no tools) | 73% ↗ | not reported | — | — |
| GPQA (with tools) | 75% ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 15.5% ↗ | not reported | — | — |
| LiveCodeBench | 68.3% ↗ | not reported | — | — |
| SWE-Bench (OpenHands) | 38.8% ↗ | not reported | — | — |
| Only NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 reports · 4 | ||||
| SWE-bench Verified | not reported | 69.7% ↗ | — | — |
| GPQA Diamond | not reported | 87.9% ↗ | — | — |
| BrowseComp | not reported | 41.4% ↗ | — | — |
| Terminal-Bench 2.1 | not reported | 53.9% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is NVIDIA Nemotron 3 Nano 30B-A3B BF16 minus NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | NVIDIA Nemotron 3 Nano 30B-A3B BF16 | NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text | Tie |
| Released | 2025-12-15 | 2026-06-04 | — |
| Cited benchmark scores | 10 | 6 | — |
Reliability
NVIDIA status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
NVIDIA Nemotron 3 Nano 30B-A3B BF16 vs …
Models sharing the most benchmarksMore matchups
NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run NVIDIA Nemotron 3 Nano 30B-A3B BF16 and NVIDIA Nemotron 3 Ultra 550B-A55B NVFP4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.