Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

45944

1/1Pass

SpreadsheetBench task 45944. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-45944
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): G4:G6, G11:G13, G20:G22 Expected answer sheet(s): Task: I'm having issues with a nested IF statement that should compare the names and start dates between a table and data located outside the table in an Excel sheet. My current formula correctly compares this information when the table and the outside cells are in matching positions. However, it fails when the positions don't correspond, as shown in my second screenshot where some true/false values are manually typed for illustration. The formula I used in the first screenshot is '=IF(Table1[@[PARTICIPANT_NAME]]=D4,IF(Table1[@[START_DATE]]>=E4, TRUE()),)'. What I need is a formula that correctly works even when the positions don't match, and the people in the table are not located in the same rows as the people outside of it. An example file is attached for reference. My current formula is: IF(Table1[@[PARTICIPANT_NAME]]=D4,IF(Table1[@[START_DATE]]>=E4,TRUE()),) please place the right formula in column G for other 2 tables.

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