NVIDIA, open weights

# Nemotron 3 Ultra

> Nemotron 3 Ultra by NVIDIA, released June 2026. Ranked #113 of 354 with a Noometry Index of 42.5. API: $0.50 in / $2.20 out per M tokens. 262K context. Scores, sources and comparisons.
- Canonical page: https://noometry.com/models/nemotron-3-ultra
- Last updated: 2026-10-10
- Title: Nemotron 3 Ultra Benchmarks, Price & Rank (October 2026)

Nemotron 3 Ultra by NVIDIA ranks 113th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.5. Its strongest category is writing & preference, where it ranks 36th. API pricing starts at $0.50 per million input tokens and $2.20 per million output tokens, with a 262K-token context window.

Last verified October 10, 2026

## Specifications

- **Noometry rank:** #113 of 354
- **Index score:** 42.5
- **Evidence:** Confirmed 30 results
- **Provider:** [![](/logos/nvidia.svg) NVIDIA](https://noometry.com/providers/nvidia)
- **Released:** June 4, 2026
- **Weights:** Open weights
- **Reasoning:** Yes
- **Context window:** 262K
- **Max output:** 128K
- **Input price:** $0.50 / M
- **Output price:** $2.20 / M
- **Blended price:** $0.93 / M
- **Output speed:** Not measured
- **Value:** #104 of 219
- **Knowledge cutoff:** Unknown
- **Input:** text
- **Hugging Face:** [nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16)

## Category scores

Each category score combines every public result we have in that category.

Nemotron 3 Ultra category scores

1.  Coding 38.1
2.  Agentic & Tool Use 23.4
3.  Reasoning 31.0
4.  Math 35.3
5.  Knowledge 52.5
6.  Multilingual 53.5
7.  Instruction Following 74.7
8.  Long Context 43.9
9.  Writing & Preference 66.3
10.  020406080

Nemotron 3 Ultra category ranks
| Category | Score | Rank | Results |
| --- | --- | --- | --- |
| [Coding](https://noometry.com/best/coding) | 38.1 | #182 | 4 |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 23.4 | #126 | 1 |
| [Reasoning](https://noometry.com/best/reasoning) | 31.0 | #82 | 6 |
| [Math](https://noometry.com/best/math) | 35.3 | #187 | 3 |
| [Knowledge](https://noometry.com/best/knowledge) | 52.5 | #61 | 2 |
| [Multilingual](https://noometry.com/best/multilingual) | 53.5 | #64 | 1 |
| [Instruction Following](https://noometry.com/best/instruction-following) | 74.7 | #88 | 1 |
| [Long Context](https://noometry.com/best/long-context) | 43.9 | #81 | 1 |
| [Writing & Preference](https://noometry.com/best/writing) | 66.3 | #36 | 4 |

## Strengths and weaknesses

Categories where Nemotron 3 Ultra places highest and lowest among the models ranked in each, with its score against that category's median.

### Strongest categories

Nemotron 3 Ultra: strongest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Writing & Preference](https://noometry.com/best/writing) | 66.3 | +12.5 | #36 of 312, top 12% |
| [Knowledge](https://noometry.com/best/knowledge) | 52.5 | +15.2 | #61 of 314, top 20% |
| [Multilingual](https://noometry.com/best/multilingual) | 53.5 | +6.1 | #64 of 297, top 22% |

### Weakest categories

Nemotron 3 Ultra: weakest categories
| Category | Score | vs median | Rank |
| --- | --- | --- | --- |
| [Agentic & Tool Use](https://noometry.com/best/agentic) | 23.4 | −6.9 | #126 of 154, top 82% |
| [Math](https://noometry.com/best/math) | 35.3 | −1.3 | #187 of 327, top 58% |
| [Coding](https://noometry.com/best/coding) | 38.1 | −0.6 | #182 of 340, top 54% |

## Closest competitors

The models ranked just above and below Nemotron 3 Ultra. When scores are this close, price and speed are often the better way to choose.

Models ranked closest to Nemotron 3 Ultra
| Model | Rank | Score | Blended $/M | Speed |  |
| --- | --- | --- | --- | --- | --- |
| [GPT-5.3 Chat](https://noometry.com/models/gpt-5-3-chat) | #109 | 42.8 | $4.81 | — | [Compare](https://noometry.com/compare/gpt-5-3-chat-vs-nemotron-3-ultra) |
| [GPT-5.5 Instant](https://noometry.com/models/gpt-5-5-instant) | #110 | 42.7 | — | — | [Compare](https://noometry.com/compare/gpt-5-5-instant-vs-nemotron-3-ultra) |
| [GPT-5.2 Codex](https://noometry.com/models/gpt-5-2-codex) | #111 | 42.6 | $4.81 | — | [Compare](https://noometry.com/compare/gpt-5-2-codex-vs-nemotron-3-ultra) |
| [Qwen3.5-Flash](https://noometry.com/models/qwen3-5-flash) | #112 | 42.5 | $0.18 | — | [Compare](https://noometry.com/compare/nemotron-3-ultra-vs-qwen3-5-flash) |
| [Hunyuan T1 20250711](https://noometry.com/models/hunyuan-t1) | #114 | 42.5 | — | — | [Compare](https://noometry.com/compare/hunyuan-t1-vs-nemotron-3-ultra) |
| [DeepSeek-R1](https://noometry.com/models/deepseek-r1) | #115 | 42.3 | $0.91 | 10 | [Compare](https://noometry.com/compare/deepseek-r1-vs-nemotron-3-ultra) |
| [Step 3.5 Flash](https://noometry.com/models/step-3-5-flash) | #116 | 42.3 | $0.15 | — | [Compare](https://noometry.com/compare/nemotron-3-ultra-vs-step-3-5-flash) |
| [Qwen3.6 27B](https://noometry.com/models/qwen3-6-27b) | #117 | 42.2 | $1.35 | — | [Compare](https://noometry.com/compare/nemotron-3-ultra-vs-qwen3-6-27b) |

Sponsored placements are available on pages like this one. [Advertise on Noometry](https://noometry.com/advertise)

## Benchmark results

Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.

### Coding

Nemotron 3 Ultra Coding benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [FrontierCode](https://noometry.com/benchmarks/frontiercode) | 13.6% | #35 of 37, top 95% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [SciCode](https://noometry.com/benchmarks/scicode) | 40.3% | #77 of 121, top 64% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [WeirdML](https://noometry.com/benchmarks/weirdml) | 43.5% | #65 of 119, top 55% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Coding](https://noometry.com/benchmarks/arena-coding) | 1468 | #60 of 294, top 21% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Agentic & Tool Use

Nemotron 3 Ultra Agentic & Tool Use benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [APEX-Agents](https://noometry.com/benchmarks/apex-agents) | 22.7% | #47 of 49, top 96% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |

### Reasoning

Nemotron 3 Ultra Reasoning benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [CritPt](https://noometry.com/benchmarks/critpt) | 3.1% | #67 of 134, top 50% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Chess Puzzles](https://noometry.com/benchmarks/chess-puzzles) | 12% | #79 of 129, top 62% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-10 |
| [LMArena Hard Prompts](https://noometry.com/benchmarks/arena-hard-prompts) | 1452 | #57 of 297, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [Mystery Game Puzzles](https://noometry.com/benchmarks/mystery-game-puzzles) | 20% | #41 of 74, top 56% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-27 |
| [DTBench](https://noometry.com/benchmarks/dtbench) | 90.1% | #40 of 151, top 27% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMCA](https://noometry.com/benchmarks/lmca) | 36.9% | #59 of 125, top 48% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [Epoch Capabilities Index](https://noometry.com/benchmarks/epoch-capabilities-index) | 146.17 | #75 of 213, top 36% |  | [Epoch AI](https://epoch.ai/eci) | 2026-06-04 |

### Math

Nemotron 3 Ultra Math benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [OTIS Mock AIME 2024-2025](https://noometry.com/benchmarks/otis-mock-aime) | 86.7% | #62 of 173, top 36% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-10 |
| [ProofBench](https://noometry.com/benchmarks/proofbench) | 2% | #74 of 77, top 97% |  | [Epoch AI](https://epoch.ai/benchmarks) |  |
| [LMArena Math](https://noometry.com/benchmarks/arena-math) | 1457 | #55 of 285, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Knowledge

Nemotron 3 Ultra Knowledge benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [GPQA Diamond](https://noometry.com/benchmarks/gpqa-diamond) | 85.4% | #63 of 186, top 34% |  | [Epoch AI](https://epoch.ai/benchmarks) | 2026-08-10 |
| [LMArena Expert](https://noometry.com/benchmarks/arena-expert) | 1472 | #48 of 273, top 18% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Multilingual

Nemotron 3 Ultra Multilingual benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Non-English](https://noometry.com/benchmarks/arena-non-english) | 1427 | #64 of 297, top 22% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Chinese](https://noometry.com/benchmarks/arena-chinese) | 1497 | #46 of 285, top 17% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena French](https://noometry.com/benchmarks/arena-french) | 1472 | #34 of 223, top 16% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena German](https://noometry.com/benchmarks/arena-german) | 1471 | #25 of 231, top 11% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Korean](https://noometry.com/benchmarks/arena-korean) | 1386 | #69 of 213, top 33% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Russian](https://noometry.com/benchmarks/arena-russian) | 1417 | #85 of 283, top 31% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Spanish](https://noometry.com/benchmarks/arena-spanish) | 1454 | #45 of 226, top 20% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Instruction Following

Nemotron 3 Ultra Instruction Following benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Instruction Following](https://noometry.com/benchmarks/arena-instruction-following) | 1418 | #77 of 298, top 26% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Long Context

Nemotron 3 Ultra Long Context benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Longer Query](https://noometry.com/benchmarks/arena-longer-query) | 1437 | #69 of 291, top 24% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

### Writing & Preference

Nemotron 3 Ultra Writing & Preference benchmark results
| Benchmark | Score | Position | Setting | Source | Date |
| --- | --- | --- | --- | --- | --- |
| [LMArena Text](https://noometry.com/benchmarks/arena-text) | 1445 | #54 of 297, top 19% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [LMArena Creative Writing](https://noometry.com/benchmarks/arena-creative-writing) | 1398 | #84 of 295, top 29% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |
| [EQ-Bench Creative Writing](https://noometry.com/benchmarks/eqbench-creative-writing) | 1692 | #31 of 115, top 27% |  | [EQ-Bench](https://eqbench.com/creative_writing.html) |  |
| [LMArena Multi-Turn](https://noometry.com/benchmarks/arena-multi-turn) | 1411 | #108 of 295, top 37% |  | [LMArena](https://lmarena.ai/leaderboard/text) | 2026-10-08 |

## API pricing by provider

Nemotron 3 Ultra API prices
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
| --- | --- | --- | --- | --- |
| [fireworks](https://fireworks.ai/docs/) | $0.60 | $2.40 | $0.12 | 2026-10-10 |
| [openrouter](https://openrouter.ai/nvidia/nemotron-3-ultra-550b-a55b) | $0.50 | $2.20 | $0.10 | 2026-10-10 |
| [together](https://docs.together.ai/docs/serverless-models) | $0.60 | $3.60 | $0.20 | 2026-10-10 |

[All NVIDIA API prices →](https://noometry.com/llm-pricing/nvidia) [Estimate your cost →](https://noometry.com/tools/cost-calculator)

## Compare Nemotron 3 Ultra

-   [Nemotron 3 Ultra vs Qwen3.5-Flash](https://noometry.com/compare/nemotron-3-ultra-vs-qwen3-5-flash)
-   [Nemotron 3 Ultra vs Hunyuan T1 20250711](https://noometry.com/compare/hunyuan-t1-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs GPT-5.2 Codex](https://noometry.com/compare/gpt-5-2-codex-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs DeepSeek-R1](https://noometry.com/compare/deepseek-r1-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs GPT-5.5 Instant](https://noometry.com/compare/gpt-5-5-instant-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs Step 3.5 Flash](https://noometry.com/compare/nemotron-3-ultra-vs-step-3-5-flash)
-   [Nemotron 3 Ultra vs GPT-6 Astra](https://noometry.com/compare/gpt-6-astra-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs Claude Fable 5.1](https://noometry.com/compare/claude-fable-5-1-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs Gemini 3.8 Flash](https://noometry.com/compare/gemini-3-8-flash-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs Kimi K3](https://noometry.com/compare/kimi-k3-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs Grok 4.6](https://noometry.com/compare/grok-4-6-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs Qwen3.8 Max](https://noometry.com/compare/nemotron-3-ultra-vs-qwen3-8-max)
-   [Nemotron 3 Ultra vs GLM-5.3](https://noometry.com/compare/glm-5-3-vs-nemotron-3-ultra)
-   [Nemotron 3 Ultra vs Muse Spark 1.3](https://noometry.com/compare/muse-spark-1-3-vs-nemotron-3-ultra)

## Other NVIDIA models

-   [Nemotron 3 Nano 30B A3B](https://noometry.com/models/nemotron-3-nano-30b-a3b)40.6
-   [Nvidia Llama 3.3 Nemotron Super 49b v1.5](https://noometry.com/models/nvidia-llama-3-3-nemotron-super-49b-v1-5)40.3
-   [Nemotron 3 Super](https://noometry.com/models/nemotron-3-super)40.1
-   [Llama 3.3 Nemotron 49b Super v1](https://noometry.com/models/llama-3-3-nemotron-49b-super-v1)40.1
-   [Nemotron 3.5 Lightning](https://noometry.com/models/nemotron-3-5-lightning)40.0
-   [Llama 3.1 Nemotron 70b Instruct](https://noometry.com/models/llama-3-1-nemotron-70b-instruct)37.6
-   [Llama 3.1 Nemotron Ultra 253b v1](https://noometry.com/models/llama-3-1-nemotron-ultra-253b-v1)36.7
-   [Llama 3.1 Nemotron 51b Instruct](https://noometry.com/models/llama-3-1-nemotron-51b-instruct)35.9

## Frequently asked questions

### How good is Nemotron 3 Ultra?

Nemotron 3 Ultra by NVIDIA ranks 113th of 354 ranked models on the Noometry Index as of October 2026, with a score of 42.5. Its strongest category is writing & preference, where it ranks 36th. API pricing starts at $0.50 per million input tokens and $2.20 per million output tokens, with a 262K-token context window.

### How much does Nemotron 3 Ultra cost?

Nemotron 3 Ultra costs $0.50 per million input tokens and $2.20 per million output tokens on openrouter, with cached input at $0.10.

### What is Nemotron 3 Ultra's context window?

Nemotron 3 Ultra accepts up to 262K tokens of input and can write up to 128K tokens in one response.

### Is Nemotron 3 Ultra open source?

Yes. Nemotron 3 Ultra's weights are downloadable from Hugging Face (nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16); check the license for commercial terms.

### What are Nemotron 3 Ultra's strengths and weaknesses?

Relative to other ranked models, Nemotron 3 Ultra places best in writing & preference, knowledge, multilingual and lowest in agentic & tool use, math, coding.

### What is Nemotron 3 Ultra best at?

Its best category is writing & preference, where it ranks 36th on Noometry.

### Cite this page

Noometry. (2026). Nemotron 3 Ultra benchmarks and pricing. Retrieved October 10, 2026, from https://noometry.com/models/nemotron-3-ultra

Quote Noometry with a link back to this page. It is also available in [Markdown](https://noometry.com/md/models/nemotron-3-ultra.md).