← back
arXivMatt L. Wiemann, Lindsay M. Smith, Peter Melchior, Siddharth Mishra-Sharma, Andrew Gordon Wilson, Pavel Izmailov, Carolina Cuesta-LázaroMon, May 25, 2026, 10:50 AM PDT
score 16.5

New benchmark tests if AI can discover unknown physics laws

Original: DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking

Source: arxiv.org

Writing ELI5 summary…