Compare AI models

Specifications
Parameters
51B—
Context window
128k128k
Benchmarks
MMLU
80.2%81.9%
GSM8K
91.43%90.9%
Overview
CompanyNVIDIAZ.ai
Release dateSep 23 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 51B and GLM-4-Air are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). GLM-4-Air shipped 110 days before Llama 3.1 Nemotron 51B, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (Llama 3.1 Nemotron 51B) vs 128k (GLM-4-Air). Llama 3.1 Nemotron 51B is open weight, while GLM-4-Air is closed.

On MMLU, GLM-4-Air leads at 81.9% vs Llama 3.1 Nemotron 51B at 80.2%. On GSM8K, Llama 3.1 Nemotron 51B leads at 91.43% vs GLM-4-Air at 90.9%.