@article{trainbeforetestharmonizeslanguagemodelra,
  title = {Train-before-Test Harmonizes Language Model Rankings},
  author = {Guanhua Zhang and Ricardo Dominguez-Olmedo and Moritz Hardt},
  year = {2025},
  eprint = {2507.05195},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.05195},
}