NVIDIA Nemotron 3 Nano 30B-A3B BF16 vs NVIDIA Nemotron 3 Super 120B-A12B
| Spec | NVIDIA Nemotron 3 Nano 30B-A3B BF16 | NVIDIA Nemotron 3 Super 120B-A12B |
|---|---|---|
| Respan Index | 15.6 (#158) | 19.1 (#135) |
| Blended price per 1M | $0.088 | $0.197 |
| Context window | 1M | 1M |
| Input / output per 1M | $0.05 / $0.2 | $0.102 / $0.48 |
| Max output | - | - |
| Input | text | text |
| Released | 2025-12-15 | 2026-03-11 |
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.
| Category | NVIDIA Nemotron 3 Nano 30B-A3B BF16 | NVIDIA Nemotron 3 Super 120B-A12B |
|---|---|---|
| Coding | 3.5* NVIDIA Nemotron 3 Nano 30B-A3B BF16 | 4.4 NVIDIA Nemotron 3 Super 120B-A12B |
| Agents | 13.1* NVIDIA Nemotron 3 Nano 30B-A3B BF16 | 17.1* NVIDIA Nemotron 3 Super 120B-A12B |
| Reasoning | 21.0 NVIDIA Nemotron 3 Nano 30B-A3B BF16 | 23.7 NVIDIA Nemotron 3 Super 120B-A12B |
| Knowledge & language | 10.4 NVIDIA Nemotron 3 Nano 30B-A3B BF16 | 17.4 NVIDIA Nemotron 3 Super 120B-A12B |
| Human preference | 34.3 NVIDIA Nemotron 3 Nano 30B-A3B BF16 | 40.3 NVIDIA Nemotron 3 Super 120B-A12B |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
NVIDIA Nemotron 3 Super 120B-A12B leads on 8 of the 8 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 Super 120B-A12B?
NVIDIA Nemotron 3 Super 120B-A12B scores 19.1 on the Respan Index (#135), ahead of NVIDIA Nemotron 3 Nano 30B-A3B BF16 at 15.6 (#158). NVIDIA Nemotron 3 Super 120B-A12B leads on 8 of the 8 benchmarks both report.
Which is cheaper, NVIDIA Nemotron 3 Nano 30B-A3B BF16 or NVIDIA Nemotron 3 Super 120B-A12B?
NVIDIA Nemotron 3 Nano 30B-A3B BF16 lists at $0.05 input and $0.2 output per 1M tokens; NVIDIA Nemotron 3 Super 120B-A12B at $0.102 and $0.48. NVIDIA Nemotron 3 Nano 30B-A3B BF16 is 2.2x cheaper per token at list price.
Which has the larger context window?
Both accept 1M tokens of context.
Compare other models
- vsNVIDIA Nemotron 3 Nano 30B-A3B BF16 vs Amazon Nova 2 Lite
- vsNVIDIA Nemotron 3 Nano 30B-A3B BF16 vs GPT-4.1 mini
- vsNVIDIA Nemotron 3 Nano 30B-A3B BF16 vs GPT-4o
- vsNVIDIA Nemotron 3 Super 120B-A12B vs GPT-4.1
- vsNVIDIA Nemotron 3 Super 120B-A12B vs Qwen3.5-Plus
- vsNVIDIA Nemotron 3 Super 120B-A12B vs Claude 3.7 Sonnet