{"kind":"task","effective_mode":"full","benchmark":{"kind":"benchmark","effective_mode":"full","slug":"bigcodebench","formal_name":"BigCodeBench","introduction":"BigCodeBench poses 1,140 function-level tasks drawn across 139 libraries. It tests whether a model can compose several real APIs correctly rather than write one self-contained function.","introduction_ja":"","introduction_en":"","category":"Category not supplied","task_count":null,"acquisition_status":"Acquisition status not supplied","official_url":"https://bigcode-bench.github.io/","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":"7dbbba4a-4324-52e7-9642-cf66daa470aa","task_key":"default--v0~2e1~2e0~5fhf--7dbbba4a-4324-52e7-9642-cf66daa470aa","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 7dbbba4a-4324-52e7-9642-cf66daa470aa","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import time\\nimport numpy as np\\ndef task_func(samples=10, delay=0.1):\\n\",\"complete_prompt\":\"import time\\nimport numpy as np\\n\\n\\ndef task_func(samples=10, delay=0.1):\\n    \\\"\\\"\\\"\\n    Make a delay for a given amount of time for a specified number of samples,\\n    measure the actual delay and calculate the statistical properties of the\\n    delay times.\\n\\n    Parameters:\\n    - samples (int): Number of samples for which the delay is measured.\\n                     Default is 10.\\n    - delay (float): Amount of time (in seconds) for each delay.\\n                     Default is 0.1 second.\\n\\n    Returns:\\n    tuple: The mean and standard deviation of the delay times.\\n\\n    Requirements:\\n    - time\\n    - numpy\\n\\n    Example:\\n    >>> mean, std = task_func(samples=5, delay=0.05)\\n    >>> print(f'Mean: %.3f, Std: %.1f' % (mean, std))\\n    Mean: 0.050, Std: 0.0\\n    >>> mean, std = task_func(100, 0.001)\\n    >>> print(f'Mean: %.3f, Std: %.4f' % (mean, std))\\n    Mean: 0.001, Std: 0.0000\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Make a delay for a given amount of time for a specified number of samples, measure the actual delay and calculate the statistical properties of the delay times.\\nThe function should output with:\\n    tuple: The mean and standard deviation of the delay times.\\nYou should write self-contained code starting with:\\n```\\nimport time\\nimport numpy as np\\ndef task_func(samples=10, delay=0.1):\\n```\",\"libs\":\"['numpy', 'time']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}