{"work":{"id":"7018fa84-745f-452a-aaa9-075fdc9a8718","openalex_id":null,"doi":null,"arxiv_id":"2406.04770","raw_key":null,"title":"Wildbench: Benchmarking llms with challenging tasks from real users in the wild, 2024 a","authors":null,"authors_text":"Bill Yuchen Lin, Yuntian Deng, Khyathi Chandu, Faeze Brahman, Abhilasha Ravichander, Valentina Pyatkin, Nouha Dziri, Ronan Le Bras, and Yejin Choi","year":2024,"venue":null,"abstract":null,"external_url":"https://arxiv.org/abs/2406.04770","cited_by_count":null,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-05-23T22:38:32.535120+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T05:55:30.305199+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":true,"display_title":"Wildbench: Benchmarking llms with challenging tasks from real users in the wild, 2024 a","render_title":"Wildbench: Benchmarking llms with challenging tasks from real users in the wild, 2024 a"},"hub":{"state":{"work_id":"7018fa84-745f-452a-aaa9-075fdc9a8718","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":17,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2024-08-28T05:53:46+00:00","last_pith_cited_at":"2026-05-20T12:21:15+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-11T20:09:00.606026+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"dataset","n":2},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"use_dataset","n":2},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}