Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

55060

1/1Pass

SpreadsheetBench task 55060. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-55060
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): Expected answer region(s): J23:N23 Expected answer sheet(s): Task: How do I create a formula in Microsoft Excel that will make cell J23 exactly replicate the value selected in cell I12, but ensure that if cell I12 is blank, cell J23 will also be blank? Currently, I face an issue where either J23 is left blank or displays 'False' when I12 has a value, or it shows the correct value when I12 is not blank but defaults to display a date like 01/01/1900 when I12 is blank. My current formula is: IF(I12="","")

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