SpreadsheetBench
157-4
SpreadsheetBench task 157-4. 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): E9:M83 Expected answer region(s): 'Sheet1'!E9:M83 Expected answer sheet(s): Sheet1 Task: I need to create a macro that will delete entire rows within the range of F14 to M83 on my worksheet if all the cells in each row from F to M are empty. I have an issue with the macro I have devised; for example, my attempt included 'Sheets("Sheet4").Range("F & i:L & j").Value = "" Then rng.EntireRow.Delete' which does not work. Additionally, it's necessary to address the problem where, if all cells are empty within the specified range, running the macro causes an error on the 'Clear Contents' part of the code. IMPORTANT: delete any row where columns F - L are blank, keeping only rows that have content in at least one cell.
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 |
| Gemini 3.1 Pro | dual | 1/1 | Pass | Share pagePublic trace |