Compare AI models

Specifications
Parameters
8B—
Context window
4k128k
Benchmarks
MMLU
54.4%90.8%
Overview
CompanyNVIDIAOpenAI
Release dateNov 15 2023Feb 27 2025
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GPT-4.5 leads Nemotron-3 8B on 1 of the 1 benchmark they both report (MMLU). Nemotron-3 8B shipped 470 days before GPT-4.5, so benchmark comparisons should account for the intervening progress.

Context windows are 4k (Nemotron-3 8B) vs 128k (GPT-4.5). Nemotron-3 8B is open weight, while GPT-4.5 is closed.

On MMLU, GPT-4.5 leads at 90.8% vs Nemotron-3 8B at 54.4%.