On Thursday, researchers at contract review and drafting startup LegalOn Technologies announced the results of a new study in which two popular generative AI large language models (LLMs)—OpenAI’s GPT-4 and Anthropic’s Claude 2—passed the Multistate Professional Responsibility Exam (MPRE). The MPRE, which tests takers on principles of legal ethics, is required for admission to the bar in all but two U.S. jurisdictions.

In March 2023, researchers announced that OpenAI’s GPT-4 model had passed the Uniform Bar Exam (UBE), with scores that would place it in the 90th percentile of test-takers. “LegalOn’s study extends this discovery, revealing that these models can also navigate complex rules and fact patterns around professional responsibility,” the press release stated. It added, “This milestone underscores the potential for AI to assist lawyers in legal work and demonstrates the increasingly advanced capabilities of large language models applied to law.”