Compare AI models

Specifications
Parameters
7B51B
Context window
4k128k
Benchmarks
GSM8K
88.2%91.43%
Overview
CompanyDeepSeekNVIDIA
Release dateFeb 5 2024Sep 23 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 51B leads DeepSeek-Math on 1 of the 1 benchmark they both report (GSM8K). DeepSeek-Math shipped 231 days before Llama 3.1 Nemotron 51B, so benchmark comparisons should account for the intervening progress.

DeepSeek-Math has 7B parameters, while Llama 3.1 Nemotron 51B has 51B. Context windows are 4k (DeepSeek-Math) vs 128k (Llama 3.1 Nemotron 51B).

On GSM8K, Llama 3.1 Nemotron 51B leads at 91.43% vs DeepSeek-Math at 88.2%.