Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

51-12

1/1Pass

SpreadsheetBench task 51-12. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-51-12
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:M7 Expected answer region(s): B6 Expected answer sheet(s): Sheet1 Task: How can I create a VBA code that will count the number of times a value in a range from A1 to M1 on an Excel sheet increases by at least 10% from a reference cell, beginning the count from A1 and restarting the counting process from the cell immediately right of each cell where a 10% increase is found, terminating the count before M1 if there is no further data, and display the count in cell B6? Additionally, I'm looking to include the ability to update the data range in the code, as the actual worksheet data range is L26 to SHA26.

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