Compare AI models

Specifications
Parameters
9B—
Context window
128k128k
Benchmarks
HumanEval
82.3%75.7%
Overview
CompanyZ.aiZ.ai
Release dateJul 5 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

CodeGeeX4-ALL-9B leads GLM-4-Air on 1 of the 1 benchmark they both report (HumanEval). GLM-4-Air shipped 30 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (CodeGeeX4-ALL-9B) vs 128k (GLM-4-Air). CodeGeeX4-ALL-9B is open weight, while GLM-4-Air is closed.

On HumanEval, CodeGeeX4-ALL-9B leads at 82.3% vs GLM-4-Air at 75.7%.