{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"simpleqa","formal_name":"SimpleQA","introduction":"SimpleQA collects short fact-seeking questions that have exactly one indisputable answer, measuring both how often a model is right and how often it declines. The format is deliberately narrow so that grading is not itself contestable.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://github.com/openai/simple-evals","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":"75886235-7851-5f40-9d16-33d8ee310f5e","task_key":"default--test--75886235-7851-5f40-9d16-33d8ee310f5e","task_revision_id":"1","upstream_id":"","short_description":"In which month and year did Apple add the ability for users to speak \"Hey Siri\"…","config":"default","split":"test","body":"{\"problem\":\"In which month and year did Apple add the ability for users to speak \\\"Hey Siri\\\" to enable the assistant without the requirement of physically handling the device?\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/openai/simple-evals","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}