Compare AI models

Specifications
Parameters
7B/13B/34B—
Context window
16k—
Benchmarks
HumanEval
48.8%72%
Overview
CompanyMetaZ.ai
Release dateAug 24 2023Jan 16 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

GLM-4 leads Code Llama on 1 of the 1 benchmark they both report (HumanEval). Code Llama shipped 145 days before GLM-4, so benchmark comparisons should account for the intervening progress.

Code Llama is open weight, while GLM-4 is closed.

On HumanEval, GLM-4 leads at 72% vs Code Llama at 48.8%.