Ralph Losey’s article evaluates the legal reasoning abilities of six advanced AI models from OpenAI and Google using a real 2024 Bar Exam essay question. Despite the high expectations, results varied significantly, with ChatGPT 4.0 emerging as the strongest contender, earning an A- for its relevant case citations and understanding of the Uniform Commercial Code (UCC). In contrast, some models, like Gemini Advanced, hallucinated information, revealing weaknesses. The findings suggest that while AI can match the average lawyer’s analytical skills, it still falls short of human expertise in nuanced legal analysis, emphasizing the need for continued human oversight and verification in legal practice.