"Can AI Ace Your Exam? A Penn Law Experiment," by Prof. R. Polk Wagner

A controlled experiment by University of Pennsylvania law professor R. Polk Wagner tested a leading large language model on 11 real final exams from Spring 2026. The model passed all 10 exams for which grades were returned, reached or exceeded the class median on each, and placed in the top decile on seven. It outscored every enrolled student on two exams, while graders often detected its work through stylistic clues.
Ad
0Like0Dislike0Comments0Shares






Comments 0
No comments yet. Be the first to share your view in the app.
Join the discussion: comments and votes are in the free Beloud app.