Compare AI models

Specifications
Parameters
—6B
Context window
128k8k
Benchmarks
HumanEval
83.7%35.9%
Overview
CompanyOpenAIZ.ai
Release dateNov 6 2023Jul 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4 Turbo leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 104 days before GPT-4 Turbo, so benchmark comparisons should account for the intervening progress.

Context windows are 128k (GPT-4 Turbo) vs 8k (CodeGeeX2-6B). GPT-4 Turbo is closed, while CodeGeeX2-6B is open weight.

On HumanEval, GPT-4 Turbo leads at 83.7% vs CodeGeeX2-6B at 35.9%.