arXivYifan Luo, Zhengying Liu, Yang Yuan, Zhilin Yang, Andrew Chi-Chih YaoThu, Nov 5, 2026, 4:58 AM PST
score 16.7
New benchmark tests AI models on open theoretical computer science problems
Original: TCSExam: Evaluating Frontier LLMs on the Full Range of TCS Research
Source: arxiv.org ↗
Writing ELI5 summary…