@misc{lin2024wildbench,
  title = {{WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild}},
  author = {Lin, Bill Yuchen and Deng, Yuntian and Chandu, Khyathi and Brahman, Faeze and Ravichander, Abhilasha and Pyatkin, Valentina and Dziri, Nouha and Le Bras, Ronan and Choi, Yejin},
  year = {2024},
  doi = {10.48550/arXiv.2406.04770},
  eprint = {2406.04770},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.04770}
}