Compare AI models

Specifications
Parameters
7B/13B/33B/65B1.5B/4B
Context window
2k8k
Benchmarks
MMLU
63.4%54.84%
GSM8K
50.9%54.89%
Overview
CompanyMetaZ.ai
Release dateFeb 24 2023Nov 29 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

LLaMA 1 and GLM-Edge are evenly matched across the 2 benchmarks they both report (MMLU, GSM8K). LLaMA 1 shipped 644 days before GLM-Edge, so benchmark comparisons should account for the intervening progress.

LLaMA 1 has 7B/13B/33B/65B parameters, while GLM-Edge has 1.5B/4B. Context windows are 2k (LLaMA 1) vs 8k (GLM-Edge).

On MMLU, LLaMA 1 leads at 63.4% vs GLM-Edge at 54.84%. On GSM8K, GLM-Edge leads at 54.89% vs LLaMA 1 at 50.9%.