Nemotron 3 Ultra
NVIDIAOpen weightsReleased Jun 4, 2026
On the arena.ai Agents leaderboard, Nemotron 3 Ultra has a Net Improvement of -15.60% (—, rank #55, 95% interval -18.90%–-12.29%). Nemotron 3 Ultra is not ranked on LMArena yet; output price $2.40 per 1M tokens.
Quick answer
- Agents leaderboard
- #55 of 56 · -15.60% success
- Text (LMArena)
- No result yet
- 17NAS overall
- #51 of 55
- API price (in / out)
- $0.60 / $2.40 per 1M tokens
- Data updated
- Nov 15, 2026 · synced daily
Sources: arena.ai, LMArena, Artificial Analysis, OpenRouter
Key metrics
More from NVIDIA
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| – | NNemotron 3.5 Super VL | – | 13.6 | $0.50 | 273 |
Pricing
- Official API list price: $0.60 input and $2.40 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $1.05 per 1M tokens.
- Among 95 models with an output price, it is the #31 cheapest.
- The cheapest OpenRouter route charges $0.60 input / $2.40 output.
Sources & methodology
On the arena.ai Agents leaderboard, Nemotron 3 Ultra has a Net Improvement of -15.60% (—, rank #55, 95% interval -18.90%–-12.29%).
- arena.ai Agents — agent Net Improvement, 95% interval, sessions and rank (via the public Hugging Face dataset, CC BY 4.0).
- LMArena — Arena score (Text leaderboard with style control, the same view arena.ai shows by default), 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
Limits: Arena scores come from anonymous users voting on chats, so they reflect conversational preference rather than agent or coding benchmarks; with few votes the interval is wide and ranks move. Prices and speeds change as providers update them.
FAQ
How does Nemotron 3 Ultra do on the Agents leaderboard?
On the arena.ai Agents leaderboard, Nemotron 3 Ultra has a Net Improvement of -15.60% (—, rank #55, 95% interval -18.90%–-12.29%).
What rank is Nemotron 3 Ultra right now?
Nemotron 3 Ultra has not been scored by LMArena yet, so it is not ranked here.
What does Nemotron 3 Ultra cost via API?
Input $0.60 / output $2.40 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $1.05 per 1M tokens.
How fast is Nemotron 3 Ultra?
Artificial Analysis measures about 254 output tokens per second, 1.2 s to the first token and 10 s to the first answer token; it is a reasoning model, so latency includes thinking time.
Is Nemotron 3 Ultra open source? Can it be self-hosted?
Nemotron 3 Ultra is an open-weights model (license: —); you can download the weights and self-host.
What is the context length of Nemotron 3 Ultra?
262K (262,144 tokens, as listed on OpenRouter).
Where does the Nemotron 3 Ultra data come from and how often is it updated?
Agent success rates come from the arena.ai Agents leaderboard (CC BY 4.0), Text scores from LMArena, intelligence and speed from Artificial Analysis, and prices and context from official list prices and OpenRouter. 17NAS syncs daily at 06:20 UTC; this page was last updated Nov 15, 2026.