SpreadsheetBench
9391
SpreadsheetBench task 9391. 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): Expected answer region(s): 'Front'!B2:C12 Expected answer sheet(s): Task: Create an Excel formula that takes a date from cell B1 on a 'Front' sheet, searches for that date in column A on a 'Data' sheet, and retrieves a corresponding value from column F on the 'Data' sheet associated with a specific letter. I'm familiar with using Index, Offset, and Match functions but am struggling to apply them successfully in this situation. Additionally, when data is added to the 'Data' sheet with new date ranges, the order of names might change or some may be absent. Is there a solution that can address this issue and ensure accurate data retrieval when the order of agents is not consistent? Make sure that the formula, that for any dates that do not exist in the Data sheet, returns a blank rather than error or zero.
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 |