Compare AI models

Specifications
Parameters
70B—
Context window
128k—
Benchmarks
MMLU
83.8%81.5%
GSM8K
84.7%87.6%
Overview
CompanyNVIDIAZ.ai
Release dateOct 15 2024Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

Llama 3.1 Nemotron 70B and GLM-4 are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). GLM-4 shipped 273 days before Llama 3.1 Nemotron 70B, so benchmark comparisons should account for the intervening progress.

Llama 3.1 Nemotron 70B is open weight, while GLM-4 is closed.

On MMLU, Llama 3.1 Nemotron 70B leads at 83.8% vs GLM-4 at 81.5%. On GSM8K, GLM-4 leads at 87.6% vs Llama 3.1 Nemotron 70B at 84.7%.