Compare AI models

Specifications
Parameters
8B—
Context window
4k128k
Benchmarks
MMLU
54.4%84.7%
Overview
CompanyNVIDIAOpenAI
Release dateNov 15 2023Nov 6 2023
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4 Turbo leads Nemotron-3 8B on 1 of the 1 benchmark they both report (MMLU). GPT-4 Turbo shipped 9 days before Nemotron-3 8B, so benchmark comparisons should account for the intervening progress.

Context windows are 4k (Nemotron-3 8B) vs 128k (GPT-4 Turbo). Nemotron-3 8B is open weight, while GPT-4 Turbo is closed.

On MMLU, GPT-4 Turbo leads at 84.7% vs Nemotron-3 8B at 54.4%.