Llama 3.1 Nemotron Ultra 253B v1 vs R1 1776
NVIDIA vs Perplexity — benchmarks, pricing, and capabilities side by side.
- •R1 1776 has the higher intelligence index (95.4 vs 78.3)
- •R1 1776 is cheaper ($0.00 vs $0.60 per 1M input)
| Llama 3.1 Nemotron Ultra 253B v1 | R1 1776 | |
|---|---|---|
| Intelligence index | 78.3 | 95.4 |
| Developer | NVIDIA | Perplexity |
| Type | LLM | LLM |
| Access | Open weights | — |
| Context window | — | — |
| Input price | $0.60 / 1M | $0.00 / 1M |
| Output price | $1.80 / 1M | $0.00 / 1M |
| Speed | 42 tok/s | — |
| Released | April 7, 2025 | February 18, 2025 |
| Parameters | 253000000000 | — |
| Input modalities | — | — |
| Output modalities | — | — |
Shared benchmarks
Llama 3.1 Nemotron Ultra 253B v1
R1 1776
MATH-500
97
95.4