SpreadsheetBench
192-22
SpreadsheetBench task 192-22. 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): D1:F71 Expected answer region(s): 'Sheet1'!F2:F71 Expected answer sheet(s): Sheet1 Task: I need a VBA code on Sheet1 that scans every populated cell in column D and checks whether the text contains any of the following keywords (case-insensitive, partial match allowed): ‘Core Activation’, ‘Core Design’, ‘Mobile Terminology’, ‘Mobile Design’, ‘Mobile Integration’, ‘Testing Layer’, ‘Testing Offshore’, ‘Carrier’, and ‘Barrier’. If a match is found, output the text “Billing PO” in the corresponding row of column F; otherwise, leave column F blank. Entries in column D may include numeric or text prefixes/suffixes (for example “123-Core Design”), which must still count as valid matches. The process should handle all rows dynamically without a fixed range, preserve existing data and formatting in all other columns. If you have to, you can solve it without VBA.
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 |