SpreadsheetBench · GPT-5.4 · dual
66-24
GPT-5.4 on SpreadsheetBench: 66-24 (dual harness). Browse score, rubric, and public trace.
Prompt excerpt
Task context
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): Imported Data!'A1:I14 Expected answer region(s): 'Items Older than 30 days'!A1:I2 Expected answer sheet(s): Items Older than 30 days Task: Extract all rows from the 'Imported Data' sheet where the date in column E is more than 30 days older than the maximum date in column E, and copy them to the 'Items Older than 30 days' sheet. Include the header row and maintain the date formatting then after that delete column Z in sheet 2.
Response trace
Agent response, tools, files, and edits
On mobile, open the full trace for the best view of the agent response, tool calls, file reads, edits, and grading context.
Open mobile trace