{"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":"d542aa34-9448-5cfd-9d97-b7b7f1d29ef9","task_key":"date~5funderstanding--main--d542aa34-9448-5cfd-9d97-b7b7f1d29ef9","task_revision_id":"1","upstream_id":"","short_description":"Yesterday was April 30, 2021. What is the date one week ago from today in…","config":"date_understanding","split":"main","body":"{\"input\":\"Yesterday was April 30, 2021. What is the date one week ago from today in MM/DD/YYYY?\\nOptions:\\n(A) 05/15/2021\\n(B) 04/23/2021\\n(C) 04/15/2021\\n(D) 06/05/2021\\n(E) 04/19/2021\\n(F) 04/24/2021\"}","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":[]}