Compare AI models

Specifications
Parameters
—9B
Context window
128k128k
Benchmarks
HumanEval
83.7%82.3%
Overview
CompanyOpenAIZ.ai
Release dateNov 6 2023Jul 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

GPT-4 Turbo leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (HumanEval). GPT-4 Turbo shipped 242 days before CodeGeeX4-ALL-9B, so benchmark comparisons should account for the intervening progress.

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

On HumanEval, GPT-4 Turbo leads at 83.7% vs CodeGeeX4-ALL-9B at 82.3%.