@article{answermatchingoutperformsmultiplechoicef,
  title = {Answer Matching Outperforms Multiple Choice for Language Model Evaluation},
  author = {Nikhil Chandak and Shashwat Goel and Ameya Prabhu and Moritz Hardt and Jonas Geiping},
  year = {2025},
  eprint = {2507.02856},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2507.02856},
}