Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

58032

1/1Pass

SpreadsheetBench task 58032. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-58032
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): A2:A35 Expected answer sheet(s): Task: Recreate Sheet1 exactly as it is. Use Arial font. Make sure the titles on row 1 are bold, italicized, and properly bordered. Make sure cells on column D are filled with #CCCCCC beginning in D2. How do I create a formula in cell A2 to search through columns I:J for a person's name based on a combination of their Title and Department code? Write formula in column A and set fill color for formulated cells to #FCD5B4. Hide gridlines as appropriate.

Published trajectories

Agent runs on this task

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

ModelHarnessScoreResultLinks
GPT-5.4showcasedual1/1Pass
Gemini 3.1 Produal0/1Fail