Nemotron 3 Ultra
Nemotron 3 Ultra — NVIDIA multimodal model with an Intelligence Index of 38, a 500K-token context window and a blended price of $0.49/1M tokens.
Key specifications
| Intelligence Index | 38 |
|---|---|
| Coding Index | 49.3 |
| Agentic Index | 27.4 |
| Arena Elo | 870 |
| Context window (K tokens) | 500 |
| Blended price ($/1M tokens) | 0.5 |
| Output speed (tokens/s) | 196 |
About Nemotron 3 Ultra
The Nemotron 3 Ultra is a multimodal model from NVIDIA with an Intelligence Index of 38.0, a Coding Index of 49.3 and a 500K-token context window. It runs at a blended price of $0.49 per million tokens and generates about 196 tokens/s. It is proprietary api. Leaderboard indices are a strong signal but only part of real-world quality, which also depends on tool use, latency and task fit.
The comparisons below show how Nemotron 3 Ultra stacks up against the alternatives people most often weigh against it, with the specific numbers laid out side by side.
Frequently asked questions
Is the Nemotron 3 Ultra any good?
Nemotron 3 Ultra — NVIDIA multimodal model with an Intelligence Index of 38, a 500K-token context window and a blended price of $0.49/1M tokens.
What are the key specs of the Nemotron 3 Ultra?
See the specification table above for the full breakdown.