GPT-5.1 vs Llama 3.1 Nemotron Ultra 253B v1
OpenAI vs NVIDIA — benchmarks, pricing, and capabilities side by side.
- •GPT-5.1 has the higher intelligence index (89 vs 78.3)
- •Llama 3.1 Nemotron Ultra 253B v1 is cheaper ($0.60 vs $1.25 per 1M input)
- •GPT-5.1 is faster
| GPT-5.1 | Llama 3.1 Nemotron Ultra 253B v1 | |
|---|---|---|
| Intelligence index | 89 | 78.3 |
| Developer | OpenAI | NVIDIA |
| Type | LLM | LLM |
| Access | API only | Open weights |
| Context window | 400,000 tokens | — |
| Input price | $1.25 / 1M | $0.60 / 1M |
| Output price | $10.00 / 1M | $1.80 / 1M |
| Speed | 115 tok/s | 42 tok/s |
| Released | November 12, 2025 | April 7, 2025 |
| Parameters | — | 253000000000 |
| Input modalities | Text, Image | — |
| Output modalities | Text | — |
Shared benchmarks
GPT-5.1
Llama 3.1 Nemotron Ultra 253B v1
AIME 2025
94
72.5
GPQA Diamond
88.1
76
Humanity’s Last Exam
26.5
8.1
LiveCodeBench
86.8
66.3
MMLU-Pro
87
82.5