{"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":"7e24476e-2c84-5635-b0fe-0375c2fc90af","task_key":"default--v0~2e1~2e0~5fhf--7e24476e-2c84-5635-b0fe-0375c2fc90af","task_revision_id":"1","upstream_id":"","short_description":"BigCodeBench v0.1.0_hf 7e24476e-2c84-5635-b0fe-0375c2fc90af","config":"default","split":"v0.1.0_hf","body":"{\"code_prompt\":\"import re\\nimport numpy as np\\nfrom scipy.stats import ttest_rel\\ndef task_func(text1, text2):\\n\",\"complete_prompt\":\"import re\\nimport numpy as np\\nfrom scipy.stats import ttest_rel\\n\\ndef task_func(text1, text2):\\n    \\\"\\\"\\\"\\n    Perform a paired t-test for the number of words in two strings, only if the strings produce the same number of words.\\n    \\n    Parameters:\\n    - text1 (str), text2 (str): The two text strings.\\n    \\n    Returns:\\n    - t_statistic (float): The t-statistic, or NaN if tests cannot be performed due to unequal lengths.\\n    - p_value (float): The p-value, or NaN if tests cannot be performed due to unequal lengths.\\n    \\n    Requirements:\\n    - re\\n    - numpy\\n    - scipy\\n    \\n    Example:\\n    >>> task_func('Words, words, words.', 'And more words!')\\n    (1.7320508075688774, 0.22540333075851657)\\n    \\\"\\\"\\\"\\n\",\"entry_point\":\"task_func\",\"instruct_prompt\":\"Perform a paired t-test for the number of words in two strings, only if the strings produce the same number of words.\\nThe function should output with:\\n    t_statistic (float): The t-statistic, or NaN if tests cannot be performed due to unequal lengths.\\n    p_value (float): The p-value, or NaN if tests cannot be performed due to unequal lengths.\\nYou should write self-contained code starting with:\\n```\\nimport re\\nimport numpy as np\\nfrom scipy.stats import ttest_rel\\ndef task_func(text1, text2):\\n```\",\"libs\":\"['re', 'numpy', 'scipy']\"}","display_format":"code","language":"","answer_status":"published","assets":[],"source_url":"https://bigcode-bench.github.io/","history":"initial import","indexing_mode":"index","subproblems":[],"grids":[]}