Side by side
| Nemotron 3.5 Lightning | Nemotron 3 Ultra | |
|---|---|---|
| Lab | NVIDIA | NVIDIA |
| Listed | Aug 11, 2026 | Jun 4, 2026 |
| Input per 1M tokens | $0.10 | $0.90 |
| Output per 1M tokens | $0.30 | $3.60 |
| Cached input per 1M | $0.06 | $0.18 |
| Blended (3:1) per 1M | $0.15 | $1.58 |
| Context window | 262K | 262K |
| Max output | 236K | 183K |
| Knowledge cutoff | - | - |
| Intelligence index | 5.5 | 11.8 |
| Coding index | 26.8 | 49.3 |
| Reasoning | Yes | Yes |
| Reads images | No | No |
| Tool use | Yes | Yes |
| Structured output | Yes | Yes |
Every benchmark both are scored on
Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.
| Benchmark | Nemotron 3.5 Lightning | Nemotron 3 Ultra | Leader |
|---|---|---|---|
| Artificial Analysis Agentic Index | 3.5Artificial Analysis and OpenRouter | 20.1Artificial Analysis and OpenRouter | Nemotron 3 Ultra |
| Artificial Analysis Coding Index | 26.8Artificial Analysis and OpenRouter | 49.3Artificial Analysis and OpenRouter | Nemotron 3 Ultra |
| Artificial Analysis Intelligence Index | 5.5Artificial Analysis and OpenRouter | 11.8Artificial Analysis and OpenRouter | Nemotron 3 Ultra |
| GPQA Diamond | 70.4%Artificial Analysis and OpenRouter | 85.4%Epoch AI | Nemotron 3 Ultra |
| tau-bench (Airline) | 65.6%Artificial Analysis and OpenRouter | 72%Artificial Analysis and OpenRouter | Nemotron 3 Ultra |
More comparisons
Where these figures come from
Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See NVIDIA models, NVIDIA models, every LLM's price and our sources.