SpreadsheetBench
32789
SpreadsheetBench task 32789. 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): C4:D14 Expected answer sheet(s): Task: I need a formula for cells D4:D7 that gets the correct value in columns BD:BR, by matching the corresponding date value in column A with the primary header in row 2, and the correct secondary headers in row 3. And then formats it as a whole number. My current formula is =IFERROR(INDEX($BE$3:$BV$81,MATCH($A4,$BD$3:$BD$81,0),MATCH(CONCAT(B$2),$BE$2:$BV$2,0)),"-"), but it only contains the data for matching with the first header. Clear any values below row 7 on columns C:D
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 |