Compare AI models

Specifications
Parameters
7B—
Context window
64k128k
Benchmarks
HumanEval
83.5%75.7%
Overview
CompanyQwenZ.ai
Release dateApr 16 2024Jun 5 2024
AccessOpen WeightClosed
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads GLM-4-Air on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 50 days before GLM-4-Air, so benchmark comparisons should account for the intervening progress.

Context windows are 64k (CodeQwen1.5) vs 128k (GLM-4-Air). CodeQwen1.5 is open weight, while GLM-4-Air is closed.

On HumanEval, CodeQwen1.5 leads at 83.5% vs GLM-4-Air at 75.7%.