How Good Are Frontier Models at Physics? Expert Re-Grading Reveals Broken Evaluations and Near-Saturation of Leading Benchmarks
- Computer Science > Artificial Intelligence arXiv:2609.13009 (cs) Authors:Ali Ansari, Haoran Sun, Andy Zeyi Liu, Mark Jabbour, Yongshan Ding, Steven Girvin, Yu He, Sohrab Ismail-Beigi, Aleksander Kubica, Owen D.
- Miller, Corey O'Hern, Vidvuds Ozolins, David Poland, A.
Unverified
- Computer Science > Artificial Intelligence arXiv:2609.13009 (cs) Authors:Ali Ansari, Haoran Sun, Andy Zeyi Liu, Mark Jabbour, Yongshan Ding, Steven Girvin, Yu He, Sohrab Ismail-Beigi, Aleksander Kubica, Owen D.
- Miller, Corey O'Hern, Vidvuds Ozolins, David Poland, A.
Sources: Arxiv