{"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":"2cba0eab-b31a-53f4-a416-33c2bb64e3a2","task_key":"default--v0~2e1~2e0~5fhf--2cba0eab-b31a-53f4-a416-33c2bb64e3a2","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 2cba0eab-b31a-53f4-a416-33c2bb64e3a2","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import subprocess\\nimport os\\nimport glob\\nimport time\\ndef task_func(test_dir):\\n\",\"complete_prompt\":\"import subprocess\\nimport os\\nimport glob\\nimport time\\n\\n\\ndef task_func(test_dir):\\n    \\\"\\\"\\\"\\n    Run all Python codes in a specific directory and return their execution times.\\n\\n    Parameters:\\n    - script_path (str): Path to the directory for Python code(s) to be executed.\\n    \\n    Returns:\\n    dict: A dictionary with the script names as keys and their execution times as values.\\n\\n    Requirements:\\n    - subprocess\\n    - os\\n    - glob\\n    - time\\n\\n    Example:\\n    >>> task_func(\\\"/mnt/data/mix_files/\\\")\\n    {'script1.py': 0.04103803634643555, \\\"script2.py\\\": 5}\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Run all Python codes in a specific directory and return their execution times.\\nThe function should output with:\\n    dict: A dictionary with the script names as keys and their execution times as values.\\nYou should write self-contained code starting with:\\n```\\nimport subprocess\\nimport os\\nimport glob\\nimport time\\ndef task_func(test_dir):\\n```\",\"libs\":\"['glob', 'subprocess', 'os', 'time']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}