top of page
newbits.ai logo – your guide to AI Solutions with user reviews, collaboration at AI Hub, and AI Ed learning with the 'From Bits to Breakthroughs' podcast series for all levels.

👉 Subscribe to NewBits Digest

🎓 OpenAI o3 Law School Study: A+ to B Grades on Legal Exams

Updated: Jun 23, 2025

OpenAI logo, featured in article on OpenAI o3 law school study, highlighting the model’s A+ to B performance across 2025 law finals and its advancement in legal reasoning over previous generative AI models.

A new OpenAI o3 law school study from the University of Maryland’s Carey School of Law reveals that OpenAI’s latest model is outperforming its predecessors on law school exams — demonstrating not just memorization, but advanced reasoning. The model received grades ranging from A+ to B on final exams, signaling a significant leap in academic AI performance.


📚 What OpenAI o3 Law School Study Revealed


The OpenAI o3 law school study, conducted by seven law professors, tested the model across eight spring 2025 finals. Results show the model is capable of scoring at or near the top of the class in multiple core legal subjects.


📌 Key Findings


  • High performance: o3 received A+ grades in Constitutional Law, Professional Responsibility, and Property. It performed well on both essay and multiple-choice questions.


  • Improvement over past models: Prior versions of ChatGPT typically scored B’s, C’s, and D’s on similar law exams in 2022 and 2023.


  • Reasoning model: o3 doesn’t just generate text — it internally revises and evaluates tentative answers before finalizing, leading to improved reasoning and accuracy.


  • Limitations: The model scored lower (B) in Administrative Law due to a gap in knowledge about the 2024 Supreme Court case Loper Bright Enterprises v. Raimondo, which overturned the Chevron doctrine.


  • Unexpected challenges: When given access to a professor’s class notes, performance actually worsened — likely due to information overload.


🔮 What’s Next for o3 and Legal AI Testing


The OpenAI o3 law school study team plans to test how AI systems perform under deceptive conditions — such as mimicking student errors — to assess the risk of misuse in academic settings. As generative AI grows more capable, its impact on legal education and exam integrity will be watched closely.



Enjoyed this article?


Stay ahead of the curve by subscribing to NewBits Digest, our weekly newsletter featuring curated AI stories, insights, and original content—from foundational concepts to the bleeding edge.


👉 Register or Login at newbits.ai to like, comment, and join the conversation.


Want to explore more?


  • AI Solutions Directory: Discover AI models, tools & platforms.

  • AI Ed: Learn through our podcast series, From Bits to Breakthroughs.

  • AI Hub: Engage across our community and social platforms.


Follow us for daily drops, videos, and updates:


And remember, “It’s all about the bits…especially the new bits.”

Comments

bottom of page