{"id":"2502.18316","title":"WiCkeD: A Simple Method to Make Multiple Choice Benchmarks More Challenging","url":"https://codeofpaper.com/paper/2502.18316","arxiv_url":"https://arxiv.org/abs/2502.18316","published":"2025-02-25","code":"official","best":{"full_name":"ahmedselhady/wicked-benchmarks","url":"https://github.com/ahmedselhady/wicked-benchmarks","tier":"official","stars":8,"license":null,"framework":null,"language":"Python","last_commit":"2025-05-21T13:17:28"},"most_starred_community":null,"implementations":[{"full_name":"ahmedselhady/wicked-benchmarks","url":"https://github.com/ahmedselhady/wicked-benchmarks","tier":"official","stars":8,"license":null,"framework":null,"language":"Python","last_commit":"2025-05-21T13:17:28"}],"possible_matches":0}