Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

45738

0/1Fail

SpreadsheetBench task 45738. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-45738
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): E6:AB25 Expected answer sheet(s): Task: I need to automate cashflow generation for approximately 1,500 bonds where each bond has a principal amount in column A, interest in column B, payment frequency in column C (1 for annual, 2 for semi-annual, 4 for quarterly), and maturity date in column D, with date headers in row 4 from E4 to AB4. Create formulas in the range E6:AB25 that display "-" in row 5, and for rows 6-25 calculate cashflows showing interest payments at regular intervals based on the frequency working backwards from the maturity date, principal plus interest at the maturity date, and "-" for non-payment dates, then center align the entire E6:AB25 range while preserving existing number formatting.

Published trajectories

Agent runs on this task

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

ModelHarnessScoreResultLinks
GPT-5.4showcasedual0/1Fail