Evaluating Jev for content moderation
A comparison of Jev, GPT-5.6 Luna and GPT-6 Luna on four moderation datasets, including prompt trade-offs, historical cost and recorded request time.
Read the investigationInvestigations into AI systems, with the methods, code and evidence behind the results.
A comparison of Jev, GPT-5.6 Luna and GPT-6 Luna on four moderation datasets, including prompt trade-offs, historical cost and recorded request time.
Read the investigation