SpreadsheetBench
57262
SpreadsheetBench task 57262. 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): T7:T15 Expected answer sheet(s): Task: I own a small independent business and am trying to track order volumes, expenses, and profits. My aim is to automate the 'Final Price point' Column in T11:T15 in my Excel sheet. For instance, when a value is entered into cell F15 (e.g., 4), the value in cell T15 should automatically update to 32 because the 'F' column represents the unit price of 8. Similarly, if a value of 1 is entered into cell G15, cell T15 should update to 42, reflecting that the 'G' column has a unit price of 10. My attempts to create a formula using IF and OR functions have failed. I've provided the workbook for reference and would appreciate guidance on how to achieve this automation.
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 |