Llama 3.1 Nemotron Ultra 253B v1 (Reasoning): Intelligence, Performance & Price Analysis
Analysis of NVIDIA's Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more. Click on any model to compare API providers for that model. For more details including relating to our methodology, see our FAQs.
Comparison Summary
Intelligence:
Llama Nemotron Ultra Reasoning is of higher quality compared to average, with a MMLU score of 0.825 and a Intelligence Index across evaluations of 61.
Price:Llama Nemotron Ultra Reasoning is cheaper compared to average with a price of $0.90 per 1M Tokens (blended 3:1).
Llama Nemotron Ultra Reasoning Input token price: $0.60, Output token price: $1.80 per 1M Tokens.
Speed:Llama Nemotron Ultra Reasoning Input token price: $0.60, Output token price: $1.80 per 1M Tokens.
Llama Nemotron Ultra Reasoning is slower compared to average, with a output speed of 41.9 tokens per second.
Latency:Llama Nemotron Ultra Reasoning has a lower latency compared to average, taking 0.64s to receive the first token (TTFT).
Context Window:Llama Nemotron Ultra Reasoning has a smaller context windows than average, with a context window of 130k tokens.
Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Speed
Output Tokens per Second; Higher is better
Price
USD per 1M Tokens; Lower is better
Parallel Queries:
Prompt Length:
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning) Model Details
Comparisons to Llama Nemotron Ultra Reasoning
GPT-4.1
o4-mini (high)
o3
Llama 4 Maverick
Llama 4 Scout
Gemini 2.5 Pro Preview (Mar' 25)
Gemini 2.5 Flash Preview (May '25) (Reasoning)
Claude 3.7 Sonnet (Extended Thinking)
Claude 4 Sonnet (Extended Thinking)
Claude 4 Sonnet
Mistral Medium 3
DeepSeek R1
DeepSeek V3 0324 (March '25)
Grok 3 mini Reasoning (high)
Nova Premier
Qwen3 235B A22B (Reasoning)
GPT-4o (Nov '24)
Further details