Compare AI models

Specifications
Parameters
7B/67B8B
Context window
4k4k
Benchmarks
MMLU
71.1%54.4%
Overview
CompanyDeepSeekNVIDIA
Release dateNov 29 2023Nov 15 2023
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

DeepSeek-LLM leads Nemotron-3 8B on 1 of the 1 benchmark they both report (MMLU). Nemotron-3 8B shipped 14 days before DeepSeek-LLM, so benchmark comparisons should account for the intervening progress.

DeepSeek-LLM has 7B/67B parameters, while Nemotron-3 8B has 8B. Context windows are 4k (DeepSeek-LLM) vs 4k (Nemotron-3 8B).

On MMLU, DeepSeek-LLM leads at 71.1% vs Nemotron-3 8B at 54.4%.