Compare AI models

Specifications
Parameters
340B—
Context window
4k—
Benchmarks
HumanEval
73.2%72%
MMLU
78.7%81.5%
GSM8K
92.3%87.6%
Overview
CompanyNVIDIAZ.ai
Release dateJun 14 2024Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Nemotron-4 340B leads GLM-4 on 2 of the 3 benchmarks they both report (HumanEval, MMLU, GSM8K). GLM-4 shipped 150 days before Nemotron-4 340B, so benchmark comparisons should account for the intervening progress.

Nemotron-4 340B is open weight, while GLM-4 is closed.

On HumanEval, Nemotron-4 340B leads at 73.2% vs GLM-4 at 72%. On MMLU, GLM-4 leads at 81.5% vs Nemotron-4 340B at 78.7%. On GSM8K, Nemotron-4 340B leads at 92.3% vs GLM-4 at 87.6%.