{"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":"da8799ab-9bd9-545a-986f-0e6c5ce51195","task_key":"date~5funderstanding--main--da8799ab-9bd9-545a-986f-0e6c5ce51195","task_revision_id":"1","upstream_id":"","short_description":"Jane thinks today is 6/18/2019, but John thinks today is 6/19/2019. Jane is…","config":"date_understanding","split":"main","body":"{\"input\":\"Jane thinks today is 6/18/2019, but John thinks today is 6/19/2019. Jane is correct. What is the date yesterday in MM/DD/YYYY?\\nOptions:\\n(A) 06/17/2063\\n(B) 05/18/2019\\n(C) 05/20/2019\\n(D) 06/17/2019\\n(E) 05/13/2019\\n(F) 06/08/2019\"}","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":[]}