Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

9726

1/1Pass

SpreadsheetBench task 9726. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-9726
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): J2 Expected answer sheet(s): Task: How can I populate the 'Visit date' column in Table 2 with the date from the 'Visit date' column in Table 1 that is immediately prior to the 'Submission date' listed in Table 2 for each student? For example, if the 'Submission date' is 21-Jun-16, I need to retrieve the last 'Visit date' from Table 1 which would be 12-Jun-16. I attempted using an array formula {=INDEX(C2:C7,MATCH(TRUE,IF(H2=$A$2:$A$7,INDEX($C$2:$C$7<I2,0)),0))} to find the next smaller value, similar to how I calculate the next larger value, but it didn't work. INDEX(C2:C7,MATCH(TRUE,IF(H2=$A$2:$A$7,INDEX($C$2:$C$7<I2,0)),0))

Published trajectories

Agent runs on this task

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

ModelHarnessScoreResultLinks
GPT-5.4showcasedual1/1Pass