Compare AI models

Specifications
Parameters
1.5B/7B/8B/14B/32B/70B4B
Context window
—128k
Benchmarks
MATH-500
94.5%96.2%
GPQA Diamond
65.2%55.1%
Overview
CompanyDeepSeekNVIDIA
Release dateJan 20 2025May 20 2025
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek R1 Distill and Llama Nemotron Nano 4B v1.1 are evenly matched across the 2 benchmarks they both report (MATH-500, GPQA Diamond). DeepSeek R1 Distill shipped 120 days before Llama Nemotron Nano 4B v1.1, so benchmark comparisons should account for the intervening progress.

DeepSeek R1 Distill has 1.5B/7B/8B/14B/32B/70B parameters, while Llama Nemotron Nano 4B v1.1 has 4B.

On MATH-500, Llama Nemotron Nano 4B v1.1 leads at 96.2% vs DeepSeek R1 Distill at 94.5%. On GPQA Diamond, DeepSeek R1 Distill leads at 65.2% vs Llama Nemotron Nano 4B v1.1 at 55.1%.