SpreadsheetBench
399-14
SpreadsheetBench task 399-14. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.
Task prompt
What the agent was asked to do
You are solving a spreadsheet benchmark task in a real workbook. Objective: Produce the correct final workbook state for the expected answer region. What matters: - Only the values in the expected answer region will be graded. - The workbook is the answer. Instructions: 1. Read the workbook and inspect the relevant data region first. 2. Infer the required result for the provided workbook instance. 3. Write the final value(s) directly into the expected answer region. 4. Do not rely on prose, formulas in your chat response, pseudocode, or VBA as the answer unless the benchmark explicitly requires those to be written into cells. 5. If the natural-language task asks for a general method, formula, or macro, convert that into the concrete result needed for this workbook instance. 6. Keep your final text response short and only summarize the workbook cells you changed. Relevant data region(s): L6:P23 Expected answer region(s): 'Sheet1'!N7:O23 Expected answer sheet(s): Sheet1 Task: Use '等线' font throughout the entire sheet. I need a VB (Visual Basic) Code to split recorded employee hours into regular hours and overtime hours. The hours worked by employees are listed in Column N of an Excel worksheet. If the value in any cell of Column N is less than or equal to 40, it should remain unchanged. However, if the value exceeds 40, then the cell in Column N should display 40, and the amount over 40 should be hardcoded to the corresponding cell in Column O. For example, if cell N12 shows 52.62, then after the code runs, N12 should display 40 and O12 should show the difference, which would be 12.62. If you don't have access to VB, use the tools you currently have. Use #,##0.## number formatting in columns N, O, and P except for whole numbers. Use General formatting for whole numbers.
Published trajectories
Agent runs on this task
Curated dual-harness runs. Best scored run per model.
| Model | Harness | Score | Result | Links |
|---|---|---|---|---|
| GPT-5.4showcase | dual | 1/1 | Pass | Share pagePublic trace |