Compare AI models

Specifications
Parameters
—6B
Context window
128k8k
Benchmarks
HumanEval
88.6%35.9%
Overview
CompanyOpenAIZ.ai
Release dateFeb 27 2025Jul 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4.5 leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 583 days before GPT-4.5, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (GPT-4.5) vs 8k (CodeGeeX2-6B). GPT-4.5 is closed, while CodeGeeX2-6B is open weight.

On HumanEval, GPT-4.5 leads at 88.6% vs CodeGeeX2-6B at 35.9%.