Compare AI models

Specifications
Parameters
7B9B
Context window
64k128k
Benchmarks
HumanEval
83.5%82.3%
Overview
CompanyQwenZ.ai
Release dateApr 16 2024Jul 5 2024
AccessOpen WeightOpen Weight
Model detailsView modelView model

Frequently asked questions

CodeQwen1.5 leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (HumanEval). CodeQwen1.5 shipped 80 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.

CodeQwen1.5 has 7B parameters, while CodeGeeX4-ALL-9B has 9B. Context windows are 64k (CodeQwen1.5) vs 128k (CodeGeeX4-ALL-9B).

On HumanEval, CodeQwen1.5 leads at 83.5% vs CodeGeeX4-ALL-9B at 82.3%.