Normal view

Received — 2 April 2026 ⏭

Nature - Issue - nature.com science feeds
General scales unlock AI evaluation with explanatory and predictive power Lexin Zhou · Lorenzo Pacchiardi · Fernando Martínez-Plumed · Katherine M. Collins · Yael Moros-Daval · Seraphina Zhang · Qinlin Zhao · Yitian Huang · Luning Sun · Jonathan E. Prunty · Zongqian Li · Pablo Sánchez-García · Kexin Jiang-Chen · Pablo A. M. Casares · Jiyun Zu · John Burden · Behzad Mehrbakhsh · David Stillwell · Manuel Cebrian · Jindong Wang · Peter Henderson · Sherry Tongshuang Wu · Patrick C. Kyllonen · Lucy Cheke · Xing Xie · José Hernández-Orallo
Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10303-2A fully automated methodology based on rubrics capturing a broad range of cognitive and intellectual demands is illustrated using LLMs and tasks, demonstrating a new way to evaluate the capabilities of AI systems and anticipate their performance.
1 April 2026 at 08:00

General scales unlock AI evaluation with explanatory and predictive power

Nature - Issue - nature.com science feeds

By: Lexin Zhou · Lorenzo Pacchiardi · Fernando Martínez-Plumed · Katherine M. Collins · Yael Moros-Daval · Seraphina Zhang · Qinlin Zhao · Yitian Huang · Luning Sun · Jonathan E. Prunty · Zongqian Li · Pablo Sánchez-García · Kexin Jiang-Chen · Pablo A. M. Casares · Jiyun Zu · John Burden · Behzad Mehrbakhsh · David Stillwell · Manuel Cebrian · Jindong Wang · Peter Henderson · Sherry Tongshuang Wu · Patrick C. Kyllonen · Lucy Cheke · Xing Xie · José Hernández-Orallo

1 April 2026 at 08:00

Nature, Published online: 01 April 2026; doi:10.1038/s41586-026-10303-2

A fully automated methodology based on rubrics capturing a broad range of cognitive and intellectual demands is illustrated using LLMs and tasks, demonstrating a new way to evaluate the capabilities of AI systems and anticipate their performance.