{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"bbh","formal_name":"BIG-Bench Hard","introduction":"BIG-Bench Hard is the set of 23 BIG-Bench tasks on which models of the time scored below the average human rater. It is best known for showing how much chain-of-thought prompting changes the result.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://github.com/suzgunmirac/BIG-Bench-Hard","indexing_mode":"index","profile":{"resources":[],"task_format":"","scoring":"","metric":"","size":"","answer_access":"","license":"","citation":"","maintainer":"","released":"","why_hard":"","related":[],"history":"","construction":"","limitations":"","saturation":"","scores":[]}},"task_id":"024a8449-b9de-59bc-8731-2d262324df8d","task_key":"web~5fof~5flies--main--024a8449-b9de-59bc-8731-2d262324df8d","task_revision_id":"1","upstream_id":"","short_description":"Question: Sal lies. Kristian says Sal lies. Helene says Kristian lies. Inga says…","config":"web_of_lies","split":"main","body":"{\"input\":\"Question: Sal lies. Kristian says Sal lies. Helene says Kristian lies. Inga says Helene tells the truth. Michael says Inga tells the truth. Does Michael tell the truth?\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/suzgunmirac/BIG-Bench-Hard","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}