Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

50768

1/1Pass

SpreadsheetBench task 50768. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-50768
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): F12:H14 Expected answer sheet(s): Task: How can I automatically plot each risk ID from a Risk Assessment table, which includes an Impact and a Likelihood number for each risk, into a corresponding position on a matrix table based on these values? For instance, if a Risk ID has an Impact of 1 and a Likelihood of 1, it should be placed in the bottom left box of a 3x3 matrix. If multiple Risk IDs share the same Impact and Likelihood numbers, they need to be displayed in the same box, separated by commas. I need guidance on how to automate this process in Excel.

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