Compare AI models

Specifications
Parameters
—6B
Context window
200k8k
Benchmarks
HumanEval
96.3%35.9%
Overview
CompanyOpenAIZ.ai
Release dateJan 31 2025Jul 25 2023
AccessClosedOpen Weight
Model detailsView modelView model

Frequently asked questions

o3-mini leads CodeGeeX2-6B on 1 of the 1 benchmark they both report (HumanEval). CodeGeeX2-6B shipped 556 days before o3-mini, so benchmark comparisons should account for the intervening progress.

Context windows are 200k (o3-mini) vs 8k (CodeGeeX2-6B). o3-mini is closed, while CodeGeeX2-6B is open weight.

On HumanEval, o3-mini leads at 96.3% vs CodeGeeX2-6B at 35.9%.