SpreadsheetBench
262-17
SpreadsheetBench task 262-17. 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): Sheet1!A1:F14','Sheet2!A1:F14' Expected answer region(s): Sheet1'!A1:F14 Expected answer sheet(s): 'Sheet1','Sheet2' Task: How can I create ranges for header values 'Task' and 'Responsibility' without hard coding the range definitions, and then apply a multiple column sort using VBA in Excel? The macro should identify the positions of these headers dynamically and perform the sorting based on the data provided in the first worksheet, with the expected outcome detailed in the second worksheet attached to the thread. The first level sorts the "Tasks" column from small to large, and the second level sorts the "Responsibilities" column from small to large
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 | 0/1 | Fail | Share pagePublic trace |