Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

304-35

1/1Pass

SpreadsheetBench task 304-35. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-304-35
SpreadsheetBench
2 models
Dual (parsed + original)
PromptWorkbook objective and answer cells
ResponseOpen each trace to inspect tool use and edits
GradeCompare score and pass/fail by model

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): A1:F36 Expected answer region(s): A3:F36 Expected answer sheet(s): start Task: How can I delete the values in column F where there are empty cells in column E, as highlighted by the yellow cells in the 'what i need sheet' of my provided Excel file? Additionally, how can I copy the values from column A down the same column, terminating the copy process when an empty cell is encountered in column F, ensuring that index cells (identical index rows like rows 2 and 29) are not copied in the process? For example, cell A29 should not be copied into A30, nor should cell A2 be copied into A3 if row 3 is empty.

Published trajectories

Agent runs on this task

Curated dual-harness runs. Best scored run per model.

ModelHarnessScoreResultLinks
GPT-5.4showcasedual1/1Pass
Gemini 3.1 Produal1/1Pass