Model openaio1

Training model: o1
Inference model: gpt-4o-mini

Investigations

Performance

DatasetValidation accuracyTest accuracy
espionage0.850.95
potions0.70.55
southgermancredit0.52884615384615390.5486725663716814
timetravel_insurance0.950.8
titanic0.70588235294117650.7450980392156863
wisconsin0.84126984126984130.6666666666666666