NVIDIA: Llama 3.1 Nemotron Ultra 253B v1
NVIDIA's Llama 3.1 Nemotron Ultra 253B shows strong maths performance but very weak agentic and coding scores relative to its size and price, making it a poor fit for most modern business workflows.
Assessment date: April 4, 2026
Our methodology takes into account a range of factors including pricing, functionality, capabilities, benchmark performance, and real-world applicability. Rankings are reviewed and updated regularly as new models are released. Issues with our rankings? Contact us
Performance Profile
Llama-3.1-Nemotron-Ultra-253B-v1 is a large language model (LLM) optimized for advanced reasoning, human-interactive chat, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta’s Llama-3.1-405B-Instruct, it has been significantly customized using Neural Architecture Search (NAS), resulting in enhanced efficiency, reduced memory usage, and improved inference latency. The model supports a context length of up to 128K tokens and can operate efficiently on an 8x NVIDIA H100 node. Note: you must include detailed thinking on in the system prompt to enable reasoning. Please see Usage Recommendations for more.
Architecture
| Modality | Text → Text |
| Tokenizer | Llama3 |
| Parameters | 253B |
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
Model Information
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.60 | $0.000600 |
| Output | $1.80 | $0.001800 |
Live Performance
Live endpoint metrics — refreshed every 30 minutes.
