SpreadsheetBench
170-13
SpreadsheetBench task 170-13. 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:A14'Sheet2!'A1:E11,'Sheet3!'A1:A41' Expected answer region(s): 'Sheet1!'A1:A50,'Sheet2!'A1:E20,'Sheet3!'A1:A50' Expected answer sheet(s): Sheet1,Sheet2,Sheet3 Task: How can I check if a header from Sheet2 exists in the Entry column of Sheet1, and if it does, insert the same number of rows as there are in Sheet2 for that header? After insertion, I want to append the data from the matching row in Sheet1 and copy over the associated data from Sheet2 into Sheet3 under a column named 'Output'. If a header from Sheet2 does not have a corresponding entry in Sheet1, it should be ignored. An example is provided where 'Sheet2 Header - U4_ComponentPropertyForm' has various associated data that needs to be matched with a similarly titled header in Sheet1, then the process of row insertion and data appending should be repeated for each Sheet1 entry into Sheet3 till the last row of Sheet1.
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 | 0/1 | Fail | Share pagePublic trace |
| Gemini 3.1 Pro | dual | 0/1 | Fail | Share pagePublic trace |