# Nemotron 3 Ultra

NVIDIA · Open Weight · rank 118 · bench-align-v5 · Self-hosted

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/models/nemotron-3-ultra-500b  
JSON: https://modelscale.dev/api/model/nemotron-3-ultra-500b

## Facts

| Field | Value | Evidence |
| --- | --- | --- |
| Canonical id | `nemotron-3-ultra-500b` | — |
| Overall score | 46.45 | Observed 2026-10-23 · source benchlm:models |
| Context window | 1M tokens | Observed 2026-10-23 · source benchlm:models |
| Release date | 2026-06-04 | Observed 2026-10-23 · source benchlm:models |
| Access type | Open Weight | — |
| Blended $/1M (75% input / 25% output) | Unavailable | Derived from the input and output rates below |

## Capability evidence

Seven axes from the ranking source. An axis the source did not score is unavailable, not zero.

| Axis | Score | Evidence |
| --- | --- | --- |
| Agentic | 20.4 | Observed 2026-10-23 · source benchlm:models |
| Coding | 58.9 | Observed 2026-10-23 · source benchlm:models |
| Knowledge | 57.4 | Observed 2026-10-23 · source benchlm:models |
| Reasoning | 69.5 | Observed 2026-10-23 · source benchlm:models |
| Multimodal & Grounded | Unavailable | Unavailable · source benchlm:models |
| Instruction Following | 92.1 | Observed 2026-10-23 · source benchlm:models |
| Math | Unavailable | Unavailable · source benchlm:models |

## Runtime service evidence

Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim. Regional or per-endpoint measurements appear only when the API supplies them; none are modelled.

| Measurement | Value | Observed | Last good | Evidence |
| --- | --- | --- | --- | --- |
| Time to first token | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |
| Throughput | Unavailable | Unavailable | Unavailable | Unavailable · source benchlm:speed |

## Endpoint and price matrix

Every published price component, including cache reads and writes.

| Component | USD | Evidence |
| --- | --- | --- |
| Input / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Output / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache read / 1M tokens | Unavailable | Unavailable · source benchlm:pricing |
| Cache write / 1M tokens | Unavailable | Unavailable · source openrouter:pricing |
| Blended / 1M (75% input / 25% output) | Unavailable | Derived — from the input and output rates above; it has no source record of its own |
| Cost per successful task (LiveBench) | Unavailable | Fetch failed · source livebench:table |

**Self-hosted listing.** Open-weight model. Self-hosted or third-party hosted costs vary by provider and infrastructure. No hosted token rate was published for this model, so its per-token price is unavailable rather than zero.

## Workload-aware monthly cost example

10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. Derived here from the published rates above by this site's own calculator — not a figure any source published.

| Field | Value |
| --- | --- |
| Modelled monthly cost | Unavailable |
| Modelled tokens | Unavailable |
| Reason | The applicable input rate is unavailable. |

## Benchmark record

52 matched benchmark rows with their published value, unit, and provenance.

### Knowledge

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA Openness Index (Artificial Analysis Openness Index) | 83.3 | Model openness assessment | Display-only external reference | [Artificial Analysis Openness Index](https://artificialanalysis.ai/evaluations/artificial-analysis-openness-index) |
| GPQA (Graduate-Level Google-Proof Q&A) | 87 | 448 questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| GPQA-D (GPQA Diamond) | 87.0 | Graduate-level science questions | Graduate level | [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://arxiv.org/abs/2311.12022) |
| MMLU-Pro (Massive Multitask Language Understanding Professional) | 86.8 | Multiple subjects | Professional level | [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://arxiv.org/abs/2406.01574) |
| HLE (Humanity's Last Exam) | 26.7 | Expert-level questions | Frontier expert level | [Humanity's Last Exam](https://lastexam.ai/) |
| Artificial Analysis Intelligence Index | 22.9 | Cross-benchmark intelligence index | Display-only external reference | [Artificial Analysis](https://artificialanalysis.ai/) |
| AA-GPQA Diamond (Artificial Analysis GPQA Diamond) | 86.7 | Graduate-level science questions | Graduate-level science reasoning | [Artificial Analysis GPQA Diamond Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gpqa-diamond) |
| AA-HLE (Artificial Analysis Humanity's Last Exam) | 28.4 | Expert-level questions | Frontier expert reasoning | [Artificial Analysis Humanity's Last Exam Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/hle) |
| AA-Omniscience Index (Artificial Analysis Omniscience Index) | -0.4 | Knowledge questions | Broad factual knowledge | [AA-Omniscience: Knowledge and Hallucination Benchmark](https://artificialanalysis.ai/evaluations/omniscience) |
| AA-Omniscience Accuracy (Artificial Analysis Omniscience Accuracy) | 21.6 | Knowledge questions | Broad knowledge | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA-Omniscience Hallucination Rate (Artificial Analysis Omniscience Hallucination Rate) | 29.7 | Knowledge questions | Factuality | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| HLE w/o tools (Humanity's Last Exam without tools) | 26.7 | Expert-level questions | Frontier expert level | [Introducing GPT-5.4 mini and nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/) |
| GPQA Diamond (Vals) (GPQA Diamond, Vals AI run) | 86.1 | Graduate-level science questions | Expert reasoning | [Vals AI GPQA Diamond, Vals AI run leaderboard](https://www.vals.ai/benchmarks/gpqa) |
| MMLU-Pro (Vals) (MMLU-Pro, Vals AI run) | 85.8 | Academic multiple-choice questions | Broad academic knowledge | [Vals AI MMLU-Pro, Vals AI run leaderboard](https://www.vals.ai/benchmarks/mmlu_pro) |

### Coding

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Terminal-Bench 2.1 | 56.4 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| Terminal-Bench 2.0 | 56.4 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| SWE-bench Verified (Software Engineering Benchmark Verified) | 71.9 | 500 verified issues | Professional software engineering | [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://arxiv.org/abs/2310.06770) |
| LiveCodeBench v6 | 89.0 | Fresh programming problems | Competitive programming level | [LiveCodeBench official repository and release documentation](https://github.com/LiveCodeBench/LiveCodeBench) |
| SWE Multilingual | 67.7 | Multilingual software-engineering tasks | Professional software engineering | [MiniMax M2.7: Early Echoes of Self-Evolution](https://www.minimax.io/news/minimax-m27-en) |
| SciCode (Scientific Code Benchmark) | 44.6 | — | — | [BenchLM](https://benchlm.ai/benchmarks/scicode) |
| AA Coding Index (Artificial Analysis Coding Index) | 49.3 | Cross-benchmark coding index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA-SciCode (Artificial Analysis SciCode) | 40.3 | Scientific coding subproblems | Scientific programming | [Artificial Analysis SciCode Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/scicode) |
| LiveCodeBench (Vals) (LiveCodeBench, Vals AI run) | 86.0 | Competitive programming problems (easy, medium, hard) | Frontier coding | [Vals AI LiveCodeBench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/lcb) |
| SWE-bench (Vals) (SWE-bench, Vals AI run) | 69.0 | Real repository issues by human time bucket | Frontier coding agents | [Vals AI SWE-bench, Vals AI run leaderboard](https://www.vals.ai/benchmarks/swebench) |

### Reasoning

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| LongBench v2 | 61.9 | Long-context tasks | Hard long-context | [LongBench v2](https://arxiv.org/abs/2412.15204) |
| AA-LCR (Artificial Analysis Long Context Reasoning) | 67.0 | Long-context reasoning tasks | Long-context reasoning | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| MLCR-AA (Medical Long Context Reasoning (MLCR-AA)) | 11.1 | Long, fragmented medical-record reasoning | Long-context medical reasoning | [Medical Long Context Reasoning (MLCR-AA)](https://artificialanalysis.ai/evaluations/mlcr-aa) |
| CritPt (Critical Physics Tasks) | 3.1 | Research-level physics questions | Research-level physics reasoning | [CritPt Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/critpt) |

### Instruction Following

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| IFBench (Instruction Following Benchmark) | 81.7 | — | — | [BenchLM](https://benchlm.ai/benchmarks/ifbench) |
| AA-IFBench (Artificial Analysis IFBench) | 81.4 | Verifiable instruction constraints | Instruction precision | [Artificial Analysis IFBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/ifbench) |

### Multilingual

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| MMLU-ProX | 83 | Multilingual professional QA | Professional multilingual | [MMLU-ProX: A Multilingual Benchmark for Advanced Large Language Model Evaluation](https://arxiv.org/abs/2503.10497) |

### Agentic

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| AA Briefcase (Artificial Analysis Briefcase) | 876 | Professional knowledge-work tasks | Professional work | [Artificial Analysis Briefcase Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-briefcase) |
| AA AutomationBench (Artificial Analysis AutomationBench) | 3.0 | Business-process automation tasks | Agentic automation | [Artificial Analysis AutomationBench Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/automationbench-aa) |
| AA EnterpriseOps-Gym (Artificial Analysis EnterpriseOps-Gym) | 28.9 | Enterprise operations workflows | Enterprise agent operations | [Artificial Analysis EnterpriseOps-Gym Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/enterprise-ops-gym-aa) |
| AA Harvey LAB v1.0 (Artificial Analysis Harvey LAB-AA v1.0) | 81.7 | Legal agent tasks | Professional legal work | [Artificial Analysis Harvey LAB-AA Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/harvey-lab-aa) |
| AA Tau3 Banking (Artificial Analysis Tau3-Banking) | 14.2 | Banking tool-use workflows | Agentic banking workflows | [Artificial Analysis Tau3-Banking Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/tau3-banking) |
| Terminal-Bench 2.0 | 56.4 | Terminal-based software tasks | Professional software engineering | [Terminal-Bench 2.0](https://www.tbench.ai/) |
| Terminal-Bench 2.1 | 56.4 | Terminal-based software-agent tasks | Professional software engineering | [Terminal-Bench](https://www.tbench.ai/) |
| BrowseComp | 44.4 | Research questions requiring browsing | Hard web research | [BrowseComp](https://openai.com/index/browsecomp/) |
| HLE w/ tools (Humanity's Last Exam with tools) | 37.4 | Expert questions with tool use | Frontier tool-augmented reasoning | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA | 1091 | Agentic real-world work tasks | Professional agentic workflows | [DeepSeek-V4 Technical Report](https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro/blob/main/DeepSeek_V4.pdf) |
| GDPval-AA (GDPval-AA normalized) | 33.1 | Economically valuable tasks | Professional agentic workflows | [Artificial Analysis model benchmarks](https://artificialanalysis.ai/models/grok-4-3) |
| AA Agentic Index (Artificial Analysis Agentic Index) | 21.7 | Cross-benchmark agentic index | Display-only external reference | [Artificial Analysis model leaderboards](https://artificialanalysis.ai/leaderboards/models) |
| AA Terminal-Bench 4.0 (Artificial Analysis Terminal-Bench v4.0) | 0.5 | Terminal-based agent tasks | Agentic software engineering | [Artificial Analysis Terminal-Bench v4.0 Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/terminalbench-v4-0) |
| GDP.pdf (Artificial Analysis GDP.pdf) | 5.0 | Professional document-production tasks | Professional knowledge work | [GDP.pdf Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/gdp-pdf) |
| AA-AnalystAgent (Artificial Analysis AnalystAgent) | 6.3 | Spreadsheet and document analysis questions | Business and data analysis | [AA-AnalystAgent Benchmark Leaderboard](https://artificialanalysis.ai/evaluations/aa-analyst-agent) |
| τ²-bench results (τ²-Bench Tool-Agent-User Evaluation) | 83.3 | Airline, retail, and telecom customer-service task sets | Dual-control customer-service workflows | [τ²-Bench: Evaluating Conversational Agents in a Dual-Control Environment](https://arxiv.org/abs/2506.07982) |
| PinchBench | 90.0 | 23 OpenClaw agent tasks | Long-horizon agent workflows | [About PinchBench](https://pinchbench.com/about) |
| τ³-bench results (τ³-Bench Tool-Agent-User Evaluation) | 70.9 | Corrected customer-service tasks plus knowledge and voice evaluation modes | Long-horizon, multimodal, and knowledge-aware tool use | [Official τ³-bench repository and release notes](https://github.com/sierra-research/tau2-bench) |
| Terminal-Bench 2.1 (Vals) (Terminal-Bench 2.1, Vals AI run) | 50.9 | Difficult terminal tasks | Frontier agentic | [Vals AI Terminal-Bench 2.1, Vals AI run leaderboard](https://www.vals.ai/benchmarks/terminal-bench-2-1) |
| MazeBench (MazeBench: visual spatial reasoning in a 3D open world) | 0 | 100 hidden gems across 256 rooms in one open world | Long-horizon spatial planning, with single puzzles that can take over one hundred moves | [MazeBench Results](https://mazebench.com/blog?post=maze-bench-results) |

### Multimodal & Grounded

| Benchmark | Value | Tasks | Difficulty | Provenance |
| --- | --- | --- | --- | --- |
| Design Arena Website (Design Arena Website Elo) | 1145 | Website generation comparisons | Design and website generation | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |

## Lifecycle and limitations log

Lifecycle events the source associates with this model.

No lifecycle event references this model. That is not evidence the model has no lifecycle plan — only that this source published none.

## What this profile does not claim

Values are reproduced exactly as their sources published them, in the units those sources declared; none are converted, interpolated, or averaged across providers. Any field marked unavailable was attempted and not returned. Last attempted fetch for this model's score: 2026-10-23 13:17 UTC.