Compare AI models

Specifications
Parameters
—9B
Context window
200k128k
Benchmarks
HumanEval
96.3%82.3%
Overview
CompanyOpenAIZ.ai
Release dateJan 31 2025Jul 5 2024
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

o3-mini leads CodeGeeX4-ALL-9B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX4-ALL-9B shipped 210 days before o3-mini, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (o3-mini) vs 128k (CodeGeeX4-ALL-9B). o3-mini is closed, while CodeGeeX4-ALL-9B is open weight.

On HumanEval, o3-mini leads at 96.3% vs CodeGeeX4-ALL-9B at 82.3%.