Model openai41

Training model: gpt-4.1
Inference model: gpt-4o-mini

Investigations

Performance

DatasetValidation accuracyTest accuracy
espionage0.850.9
potions0.650.75
southgermancredit0.48076923076923080.3274336283185841
timetravel_insurance0.60.7
titanic0.76470588235294110.7058823529411765
wisconsin0.82539682539682540.6818181818181818