SpreadsheetBench · GPT-5.4 · dual
54638
GPT-5.4 on SpreadsheetBench: 54638 (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): Expected answer region(s): 'Sheet1'!B2:B150 Expected answer sheet(s): Task: Recreate Sheet1 exactly as it is with Calibri font. Recreate all formulas in column A of Sheet1 exactly as they are. Remove gridlines when appropriate. Hide Sheet2. How can I use a non-dynamic array formula to select and list only the unique values from a range of cells, specifically from A2:A150, and have these unique values displayed in an adjacent range, B2:B150, without using a dynamic array formula? A sample Excel file with the desired outcome in part of B2:B150 has been provided for reference. Insert this new formula into cells B2:B150 and format cells B2:B150 with gridlines and #FFFF00 fill color. Column A should only have borders up to row 13. There should be formulas all the way down to cell A150.
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