Model openai10o1

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

Investigations

Performance

DatasetValidation accuracyTest accuracy
espionage0.950.9
potions0.60.6
southgermancredit0.490384615384615360.4424778761061947
timetravel_insurance0.80.65
titanic0.78431372549019610.7058823529411765
wisconsin0.88888888888888880.7727272727272727
wisconsin0.71428571428571430.696969696969697