Quality
Highest overall scores
- 1
NVIDIA: Nemotron 3 Ultra37.8 - 2NVIDIA: Nemotron 3 Super25.4
- 3NVIDIA: Nemotron 3 Nano 30B A3B14.2
NVIDIA model benchmarks.
Compare NVIDIA models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1NVIDIA: Nemotron 3 Nano 30B A3B189 t/s
- 2NVIDIA: Nemotron 3 Ultra121 t/s
- 3NVIDIA: Nemotron 3 Super80.5 t/s
Input price
Lowest price per 1M tokens
- 1NVIDIA: Nemotron 3 Nano 30B A3B$0.05/1M
- 2NVIDIA: Nemotron 3 Super$0.08/1M
- 3NVIDIA: Nemotron 3 Ultra$0.50/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare NVIDIA model capability.
Performance and price
Compare practical tradeoffs.
All NVIDIA models.
3 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| NVIDIA: Nemotron 3 Ultra | 37.8 | 121 t/s | 512.3K | $0.50 | $2.20 | |
| NVIDIA: Nemotron 3 Super | 25.4 | 80.5 t/s | 1M | $0.08 | $0.40 | |
| NVIDIA: Nemotron 3 Nano 30B A3B | 14.2 | 189 t/s | 262.1K | $0.05 | $0.20 |
NVIDIA technical benchmarks.
Compare named evaluation records available for NVIDIA models. Missing results remain blank rather than being estimated.
| Benchmark | Area | Nemotron 3 Ultra | Nemotron 3 Super | Nemotron 3 Nano 30B A3B | Source |
|---|---|---|---|---|---|
| Intelligence Index | overallQuality | 37.8 | 25.4 | 14.2 | OpenRouter / artificial-analysis |
| Coding Index | coding | 49.3 | 37.7 | 14.4 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 27.4 | 8.7 | 2 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | — | 80 | 75.7 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | — | 19.2 | 10.2 | OpenRouter model benchmarks |
| IFBench | IFBench | — | 71.5 | 71.1 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | — | 67.8 | 40.9 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | — | 60 | 33.7 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | — | 9.9 | 0 | OpenRouter model benchmarks |
| CritPt | CritPt | — | 3.1 | 0.9 | OpenRouter model benchmarks |
| SciCode | SciCode | — | 36 | 29.6 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | — | 28.8 | 13.6 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | — | 24 | 17.1 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | — | 13 | 17.1 | OpenRouter model benchmarks |
| MMLU-Pro | Knowledge and reasoning | — | — | 78.3 | OpenEvals/leaderboard-data |