{
  "id": "lin2024wildbench",
  "type": "article-journal",
  "title": "WildBench: Benchmarking LLMs with Challenging Tasks from Real Users in the Wild",
  "author": [{"given":"Bill Yuchen","family":"Lin"},{"given":"Yuntian","family":"Deng"},{"given":"Khyathi","family":"Chandu"},{"given":"Faeze","family":"Brahman"},{"given":"Abhilasha","family":"Ravichander"},{"given":"Valentina","family":"Pyatkin"},{"given":"Nouha","family":"Dziri"},{"given":"Ronan","family":"Le Bras"},{"given":"Yejin","family":"Choi"}],
  "issued": {"date-parts":[[2024]]},
  "URL": "https://arxiv.org/abs/2406.04770",
  "DOI": "10.48550/arXiv.2406.04770",
  "genre": "Preprint",
  "archive": "arXiv",
  "number": "2406.04770",
  "custom": {
    "record_url": "https://yuntiandeng.com/wildchat/papers/wildbench/",
    "first_arxiv_submission": "2024-06-07",
    "citation_note": "Cites the arXiv preprint with its original 2024 preprint year. The paper later appeared at ICLR 2025."
  }
}