Compare AI models

Specifications
Parameters
671B253B
Context window
128k128k
Benchmarks
LiveCodeBench
65.9%66.3%
GPQA Diamond
71.5%76%
Overview
CompanyDeepSeekNVIDIA
Release dateJan 20 2025Apr 7 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama Nemotron Ultra 253B leads DeepSeek R1 on 2 of the 2 benchmarks they both report (LiveCodeBench, GPQA Diamond). DeepSeek R1 shipped 77 days before Llama Nemotron Ultra 253B, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 has 671B parameters, while Llama Nemotron Ultra 253B has 253B. Context windows are 128k (DeepSeek R1) vs 128k (Llama Nemotron Ultra 253B).

On LiveCodeBench, Llama Nemotron Ultra 253B leads at 66.3% vs DeepSeek R1 at 65.9%. On GPQA Diamond, Llama Nemotron Ultra 253B leads at 76% vs DeepSeek R1 at 71.5%.