{"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":"c4657bdd-8f4c-5ff7-8acf-8437a7100953","task_key":"date~5funderstanding--main--c4657bdd-8f4c-5ff7-8acf-8437a7100953","task_revision_id":"1","upstream_id":"","short_description":"2015 is coming in 36 hours. What is the date a month ago in MM/DD/YYYY?","config":"date_understanding","split":"main","body":"{\"input\":\"2015 is coming in 36 hours. What is the date a month ago in MM/DD/YYYY?\\nOptions:\\n(A) 03/07/2015\\n(B) 11/28/2014\\n(C) 11/23/2014\\n(D) 12/20/2014\\n(E) 12/05/2014\\n(F) 11/29/2014\"}","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":[]}