{"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":"56387073-7204-50f6-8244-5369b40b7fd9","task_key":"date~5funderstanding--main--56387073-7204-50f6-8244-5369b40b7fd9","task_revision_id":"1","upstream_id":"","short_description":"Jane got her job in 2016. Today is her 3-year work anniversary. She still…","config":"date_understanding","split":"main","body":"{\"input\":\"Jane got her job in 2016. Today is her 3-year work anniversary. She still remember that on Dec 2, her second day at work, she spilled coffee on her laptop. What is the date one week ago from today in MM/DD/YYYY?\\nOptions:\\n(A) 11/23/2019\\n(B) 06/24/2019\\n(C) 03/24/2019\\n(D) 11/24/2019\\n(E) 02/29/2020\"}","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":[]}