Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

49196

1/1Pass

SpreadsheetBench task 49196. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-49196
SpreadsheetBench
1 model
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): C2:C47 Expected answer sheet(s): Task: How can I modify the formula in column C of my Excel sheet so that it updates the year to 2022 in the date when the year in column K changes to '22, considering that the original data source uses periods instead of slashes in the date format (European style), and I want the date format to use slashes to conform to UK standards without having to manually replace each period with a slash for the data I copy in? The formula I use is LEFT(K2,2)&"/"&MID(K2,4,2)&"/"&TEXT(TODAY(),"yy")&MID(K2,FIND(" ",K2,1),6).

Published trajectories

Agent runs on this task

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

ModelHarnessScoreResultLinks
GPT-5.4showcasedual1/1Pass