General scales unlock AI evaluation with explanatory and predictive power.

Zhou L, Pacchiardi L, Martínez-Plumed F, Collins KM, Moros-Daval Y, Zhang S, Zhao Q, Huang Y, Sun L, Prunty JE, Li Z, Sánchez-García P, Jiang-Chen K, Casares PAM, Zu J, Burden J, Mehrbakhsh B, Stillwell D, Cebrian M, Wang J, Henderson P, Wu ST, Kyllonen PC, Cheke L, Xie X, Hernández-Orallo J

Open source

DOI
10.1038/s41586-026-10303-2
Published
2026 Apr
Container
Nature
Publisher
Not recorded
Open access
yes

Credibility signals

limited evidence Score 45/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1038/s41586-026-10303-2,
  title = {General scales unlock AI evaluation with explanatory and predictive power.},
  author = {Zhou L and Pacchiardi L and Martínez-Plumed F and Collins KM and Moros-Daval Y and Zhang S and Zhao Q and Huang Y and Sun L and Prunty JE and Li Z and Sánchez-García P and Jiang-Chen K and Casares PAM and Zu J and Burden J and Mehrbakhsh B and Stillwell D and Cebrian M and Wang J and Henderson P and Wu ST and Kyllonen PC and Cheke L and Xie X and Hernández-Orallo J},
  year = {2026},
  journal = {Nature},
  doi = {10.1038/s41586-026-10303-2},
  url = {https://doi.org/10.1038/s41586-026-10303-2}
}

RIS

TY  - JOUR
TI  - General scales unlock AI evaluation with explanatory and predictive power.
AU  - Zhou L
AU  - Pacchiardi L
AU  - Martínez-Plumed F
AU  - Collins KM
AU  - Moros-Daval Y
AU  - Zhang S
AU  - Zhao Q
AU  - Huang Y
AU  - Sun L
AU  - Prunty JE
AU  - Li Z
AU  - Sánchez-García P
AU  - Jiang-Chen K
AU  - Casares PAM
AU  - Zu J
AU  - Burden J
AU  - Mehrbakhsh B
AU  - Stillwell D
AU  - Cebrian M
AU  - Wang J
AU  - Henderson P
AU  - Wu ST
AU  - Kyllonen PC
AU  - Cheke L
AU  - Xie X
AU  - Hernández-Orallo J
PY  - 2026
JO  - Nature
DO  - 10.1038/s41586-026-10303-2
UR  - https://doi.org/10.1038/s41586-026-10303-2
ER  - 

APA

L, Z., L, P., F, M., KM, C., Y, M., S, Z., Q, Z., Y, H., L, S., JE, P., Z, L., P, S., K, J., PAM, C., J, Z., J, B., B, M., D, S., M, C., J, W., P, H., ST, W., PC, K., L, C., X, X., & J, H. (2026). General scales unlock AI evaluation with explanatory and predictive power.. Nature. https://doi.org/10.1038/s41586-026-10303-2

Source records