Nemotron 3 Ultra
Not tested yet
Language modelActive
Nemotron 3 Ultra
NVIDIA
- Released
- June 4, 2026
- Data date
- September 8, 2026
- Intelligence
- Overall score
- Speed
- 162.9 tokens/sOutput throughput
- Price
- Input · Output / 1M tokens
- Input
- Text
- Output
- Text
No published category-wide ranking is available for this model.
Entries 1-12 of 15. Page 1 of 2.
Measurements without matching peer values
These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.
GPQA (Show measurement, test conditions, and source)
- Source value
- 87
- Score
- 87
- Metric
- percent
- Unit
- %
- Category
- reasoning
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:0
- Source type
- vendor-reported
- Evaluator
- NVIDIA model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. no tools
LiveCodeBench (v6) (Show measurement, test conditions, and source)
- Source value
- 89
- Score
- 89
- Metric
- percent
- Unit
- %
- Category
- coding
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:1
- Source type
- vendor-reported
- Evaluator
- NVIDIA model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. official eval
MMLU-Pro (Show measurement, test conditions, and source)
- Source value
- 86.8
- Score
- 86.8
- Metric
- percent
- Unit
- %
- Category
- knowledge
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:2
- Source type
- vendor-reported
- Evaluator
- NVIDIA model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. official eval
RULER @ 1M (Show measurement, test conditions, and source)
- Source value
- 90.9
- Score
- 90.9
- Metric
- percent
- Unit
- %
- Category
- long-context
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:3
- Source type
- vendor-reported
- Evaluator
- NVIDIA model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. 1M context
SWE-Bench Verified (Show measurement, test conditions, and source)
- Source value
- 70.7
- Score
- 70.7
- Metric
- percent
- Unit
- %
- Category
- coding
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:4
- Source type
- vendor-reported
- Evaluator
- NVIDIA model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. official eval
Terminal Bench 2.1 (Show measurement, test conditions, and source)
- Source value
- 56.4
- Score
- 56.4
- Metric
- percent
- Unit
- %
- Category
- agentic
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:5
- Source type
- vendor-reported
- Evaluator
- NVIDIA model card
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Vendor-reported result. official eval
AA-Briefcase Elo (Show measurement, test conditions, and source)
- Source value
- 878.22
- Score
- 878.22
- Metric
- elo
- Unit
- elo
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:6
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
AA-Omniscience Index (Show measurement, test conditions, and source)
- Source value
- -0.4
- Score
- -0.4
- Metric
- points
- Unit
- points
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:7
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
Output speed (Show measurement, test conditions, and source)
- Source value
- 162.896137952923
- Score
- 162.896137952923
- Metric
- tokens/s
- Unit
- tokens/s
- Direction
- Higher is better
- Comparison cohort
- research:nemotron-3-ultra:8
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Time per Intelligence Index Task (Show measurement, test conditions, and source)
- Source value
- 2.7029008833572337
- Score
- 2.7029008833572337
- Metric
- minutes
- Unit
- minutes
- Direction
- Lower is better
- Comparison cohort
- research:nemotron-3-ultra:9
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Latency reasoning time (Show measurement, test conditions, and source)
- Source value
- 13.965954187676784
- Score
- 13.965954187676784
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Comparison cohort
- research:nemotron-3-ultra:10
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Latency input time (Show measurement, test conditions, and source)
- Source value
- 2.332192846
- Score
- 2.332192846
- Metric
- seconds
- Unit
- seconds
- Direction
- Lower is better
- Comparison cohort
- research:nemotron-3-ultra:11
- Source type
- independent-evaluator
- Evaluator
- Artificial Analysis
- Status
- active
- Retrieved at
- 2026-09-08
- Methodology
- Independent evaluation. unknown
- Context
- Artificial Analysis performance timing; output speed is decoded after the first streaming chunk. Provider basis: serving-provider median.
Our model tests
Community tests you can inspect
Compare how the models respond to the same prompt. Each test shows the first attempt, with no subsequent fixes to the generated code. These results do not contribute to an overall score.
Pelican on a bicycle
A community classic for free-form SVG drawing.
Prompt and test conditions
Generate an SVG of a pelican riding a bicycle
Token limit including reasoning: 8,192 tokens
Task origin (Simon Willison)Profile
Specifications and access
Published information about this model. Existing estimates are explicitly labeled.
Additional source observations
Dated documentation and model-card observations. Provider limits, native context and extended context can differ. Configuration notes retain the source wording.
- Release
- 2026-06-04Source
- Parameters
- 550 BSource
- Active parameters
- 55 BSource
- License
- OpenMDW-1.1Source
- Architecture
- LatentMoE, Mamba-2 + MoE + Attention hybrid with MTPSource
- Languages
- English, French, Spanish, Italian, German, Japanese, Hindi, Korean, Brazilian Portuguese, ChineseSource
- Input
- TextSource
- Output
- TextSource
Pricing
Published prices
Prices apply to the stated unit. Resolution, output length, and provider can change the cost.
Cost example
100 API requests
$0.24
100 requests with 1,000 input and 500 output tokens each calculate to $0.24. Input accounts for $0.06; output accounts for $0.18.
- Input price
- $0.6 / 1M tokensBase tier for each request
- Output price
- $3.6 / 1M tokensBase tier for each request
The calculation uses documented token prices and no cache discount. It excludes extra tools, tax, reasoning tokens, and further hidden output tokens.
Open sourceHead-to-head comparisons
Compare this model
Each matchup compares this model with exactly one other model from the same category.
There are no published direct comparisons for this model yet.
More models
Models from the same selection
All AI models
Evidence
Sources and data date
Every statement links to its underlying documentation or leaderboard.
- Speed
Median across serving providers. Output speed after the first streaming chunk, not total response time. Retrieved September 8, 2026.
- Price
Base API prices without caching or batch discounts. Higher context tiers and other rates are listed under Costs.
- Input
Documented modalities. Retrieved September 8, 2026.
- Output
Documented modalities. Retrieved September 8, 2026.
Research date September 8, 2026. 2 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Open evidence questions and research notes (original wording)
Not found in the inspected sources
knowledge-cutoff. No exact value located in the checked primary model card/API documentation.