Compare AI models

Specifications
Parameters
236B51B
Context window
128k128k
Benchmarks
MMLU
77.8%80.2%
GSM8K
92.2%91.43%
Overview
CompanyDeepSeekNVIDIA
Release dateMay 6 2024Sep 23 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek V2 and Llama 3.1 Nemotron 51B are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). DeepSeek V2 shipped 140 days before Llama 3.1 Nemotron 51B, so benchmark comparisons should account for the intervening progress.

DeepSeek V2 has 236B parameters, while Llama 3.1 Nemotron 51B has 51B. Context windows are 128k (DeepSeek V2) vs 128k (Llama 3.1 Nemotron 51B).

On MMLU, Llama 3.1 Nemotron 51B leads at 80.2% vs DeepSeek V2 at 77.8%. On GSM8K, DeepSeek V2 leads at 92.2% vs Llama 3.1 Nemotron 51B at 91.43%.