SpreadsheetBench
82-38
SpreadsheetBench task 82-38. 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): SH1!'A1:H35,'DATA!'A1:H35,'FAKE!'A1:H35' Expected answer region(s): 'DATA'!D2:D20 Expected answer sheet(s): DATA Task: On my SH1 sheet, there are multiple headers labeled 'INVOICE NO' with a number underneath each for different ranges. In my DATA sheet, column D should match the 'INVOICE NO' from SH1 and repeat for each header until a 'TOTAL' row, which correlates with the sheet name in column E of the DATA sheet. The invoice numbers should be arranged in the order they appear on SH1 when the sheet names match; otherwise, sheets with names that do not match should be ignored. I initially wanted formulas that do not specify a range and dynamically work up to the last row containing data. However, I encountered a problem when the DATA sheet has more data than the SH1 sheet, resulting in a #NUM! error. I want to keep the original numbers after the new ones have been filled in and only fill in column D when there is a matching sheet name in column E, while ignoring rows with unmatched names or extra data. Can you provide a solution or VBA code that addresses these issues?
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 |