NVIDIA model product
Llama 3.1 Nemotron Ultra 253B
1 405B Instruct, developed by NVIDIA using Neural Architecture Search (NAS) and vertical compression.
Updated Aug 17, 2026. Default version: Llama 3.1 Nemotron Ultra 253B v1
LLMBoard Score30.0Llama 3.1 Nemotron Ultra 253B v1
Coverage80%6 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable
Llama 3.1 Nemotron Ultra 253B Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Llama 3.1 Nemotron Ultra 253B Benchmark Results
Benchmark scores for Llama 3.1 Nemotron Ultra 253B v1.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkBFCL v2 | Score74.1% | Rank02 | Participants5 | Percentile75.0% | EvidenceC | Evaluated |
| BenchmarkMATH-500 | Score97.0% | Rank08 | Participants32 | Percentile77.4% | EvidenceC | Evaluated |
| BenchmarkIFEval | Score89.5% | Rank21 | Participants67 | Percentile69.7% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score66.3% | Rank27 | Participants75 | Percentile64.9% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score72.5% | Rank83 | Participants115 | Percentile28.1% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score76.0% | Rank105 | Participants239 | Percentile56.3% | EvidenceC | Evaluated |
Llama 3.1 Nemotron Ultra 253B Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenatext style control | Categoryoverall | Rank198 | Rating / score1347.5 | Votes2,549 | ObservationsN/A | Result date |
| Arenatext | Categoryoverall | Rank209 | Rating / score1319.5 | Votes2,549 | ObservationsN/A | Result date |
Llama 3.1 Nemotron Ultra 253B Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- N/A
- Official provider
- N/A
- Lowest third-party
- From $0.598 input, $1.79 output per 1M via Cortecs
- Tracked offerings
- 4
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderNvidia | Provider model IDnvidia/llama-3.1-nemotron-ultra-253b-v1 | Regionglobal | Input / 1MN/A | Output / 1MN/A | Context128K | Updated |
| ProviderCortecs | Provider model IDllama-3.1-nemotron-ultra-253b-v1 | Regionglobal | Input / 1M$0.598 | Output / 1M$1.79 | Context128K | Updated |
| ProviderNebius Token Factory | Provider model IDnvidia/Llama-3_1-Nemotron-Ultra-253B-v1 | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context128K | Updated |
| ProviderLLM Gateway | Provider model IDllama-3.1-nemotron-ultra-253b | Regionglobal | Input / 1M$0.60 | Output / 1M$1.8 | Context128K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Llama 3.1 Nemotron Ultra 253B Runtime Performance
Provider-specific output speed and catalog latency for Llama 3.1 Nemotron Ultra 253B v1. Runtime does not affect the capability score.
No runtime data
Browse runtime rankingsNo provider-specific speed or latency record is linked to the default version yet.
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Llama 3.1 Nemotron Ultra 253B Specifications
Technical details for the model's default version.
- Version
- Llama 3.1 Nemotron Ultra 253B v1
- Released
- Apr 7, 2025
- Knowledge cutoff
- Dec 1, 2023
- Parameters
- 253B
- Context window
- N/A
- Max output
- N/A
- Inputs
- text
- Outputs
- text
- Open weights
- No
- License
- Llama 3.1 Community License
Llama 3.1 Nemotron Ultra 253B Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionLlama 3.1 Nemotron Ultra 253B v1 | Released | LLMBoard30.0 | Parameters253B | ContextN/A | Max outputN/A | Open weightsNo | LicenseLlama 3.1 Community License |
Llama 3.1 Nemotron Ultra 253B vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Llama 3.1 Nemotron Ultra 253B
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
NV
Nemotron Nano 9B
NVIDIA
NV
Nemotron 3 Nano
NVIDIA
NV
Nemotron 3.5 Lightning
NVIDIA
NV
Llama 3.3 Nemotron Super 49B
NVIDIA
NV
Nemotron 3 Super
NVIDIA
NV
Llama 3.1 Nemotron Nano 8B
NVIDIA
What is Llama 3.1 Nemotron Ultra 253B?
Key information about Llama 3.1 Nemotron Ultra 253B and its available data.
1 405B Instruct, developed by NVIDIA using Neural Architecture Search (NAS) and vertical compression. It underwent multi-phase post-training (SFT for Math, Code, Reasoning, Chat, Tool Calling; RL with GRPO) to enhance reasoning and instruction-following. Optimized for accuracy/efficiency tradeoff on NVIDIA GPUs.
Supports 128k context.
Data as of 2026-08-17.
FAQ
Common questions about Llama 3.1 Nemotron Ultra 253B.
When was Llama 3.1 Nemotron Ultra 253B released?
Llama 3.1 Nemotron Ultra 253B's default version was released on Apr 7, 2025.
How much does Llama 3.1 Nemotron Ultra 253B cost?
No official standard PAYG price is currently available for Llama 3.1 Nemotron Ultra 253B. The lowest tracked third-party offer starts at $0.598 input and $1.79 output via Cortecs.
Who created Llama 3.1 Nemotron Ultra 253B?
Llama 3.1 Nemotron Ultra 253B was created by NVIDIA.
What is the context window for Llama 3.1 Nemotron Ultra 253B?
A context window is not available for the default version.
Is Llama 3.1 Nemotron Ultra 253B open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Llama 3.1 Nemotron Ultra 253B?
4 provider offerings are linked to the default version.
What models should I compare Llama 3.1 Nemotron Ultra 253B with?
Nearby ranked alternatives include Qwen3 VL 30B A3B Thinking, Qwen3 32B, GPT-5-nano.