SpreadsheetBench
42354
SpreadsheetBench task 42354. 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): D2:D8 Expected answer sheet(s): Task: I need a formula for Excel that evaluates cells in a row across columns A, B, and C, and returns the result in column D. The formula should prioritize a result from column A, but if column A contains #N/A, it should then consider the result from column B. If B also has #N/A, it should look to column C. Only when all three columns A, B, and C contain #N/A, column D should be left blank. The evaluation should be done for each row individually, taking the first non-#N/A value from left to right. I'm using Microsoft Office Professional Plus 2016, and I've attached the relevant file.
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 |