SpreadsheetBench
50521
SpreadsheetBench task 50521. 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): N4:N6 Expected answer sheet(s): Task: I need a formula to count the number of blank cells between the first and second numeric entries across each row of a table containing product order numbers distributed across different months. The first entry in a row should count as the start, and the second numeric entry marks the end of the count. The dataset is quite large, with thousands of customers and their monthly purchases over a few years, with blank cells representing months when no purchase occurred. The required formula should automatically calculate this for all customers. Additionally, if the first value in a row is greater than 1, the output should be 1 instead of the count. An example scenario would present the count in cell N4, and based on the provided spreadsheet example for customer 1, the correct count should be 5, which is the gap from February to June inclusive.
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 |