AI Research

    GDP.xlsx: Benchmarking Frontier Models on Professional Workbooks

    A 70-task benchmark pairs professional requests with workbooks and expert-written scoring criteria.

    We introduce GDP_xlsx, a benchmark of 70 realistic workplace requests written by professionals in 13 domains, each paired with an expert rubric of binary criteria and with the complete workbook or CSV file it refers to.

    AC

    ArXiv CS.CL

    Source

    ArXiv CS.CL
    AI Analysis

    Generated insight by OnAirToday AI

    This benchmark focuses on practical spreadsheet tasks rather than abstract tests, offering a way to assess models against workplace requests. Its expert-written binary criteria make performance on those requests easier to evaluate consistently.

    Powered by AI • Not a substitute for human analysisMore Insights →
    Read the full story at ArXiv CS.CL →
    Share
    Filed under:AI Research

    Comments

    Keep comments relevant and respectful. No links, advertising, self-promotion, or spam.

    0/1000