{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"mmlu","formal_name":"MMLU","introduction":"MMLU asks four-way multiple-choice questions across 57 subjects, from elementary material to professional-level examinations. Since 2020 it has been the most widely cited single reference point for general capability.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://github.com/hendrycks/test","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":"84c9c95b-24c2-5a0f-922a-ca6057e2ae00","task_key":"all--test--84c9c95b-24c2-5a0f-922a-ca6057e2ae00","task_revision_id":"1","upstream_id":"","short_description":"Which of the following is false?","config":"all","split":"test","body":"{\"choices\":\"['The following fully connected network without activation functions is linear: $g_3(g_2(g_1(x)))$, where $g_i(x) = W_i x$ and $W_i$ are matrices.', 'Leaky ReLU $\\\\\\\\max\\\\\\\\{0.01x,x\\\\\\\\}$ is convex.', 'A combination of ReLUs such as $ReLU(x) - ReLU(x-1)$ is convex.', 'The loss $\\\\\\\\log \\\\\\\\sigma(x)= -\\\\\\\\log(1+e^{-x})$ is concave']\",\"question\":\"Which of the following is false?\",\"subject\":\"machine_learning\"}","display_format":"text","language":"","answer_status":"published","assets":[],"source_url":"https://github.com/hendrycks/test","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}