Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

46646

0/1Fail

SpreadsheetBench task 46646. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-46646
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): B11:M11 Expected answer sheet(s): Task: How can I calculate the percentage of night shifts for a given month, considering a variable year range from 2010 to 2022. Take into account leap years and the specific days of the month. Please perform this task and fill out row 11 using the year value shown. Output the values in decimal format, such that a) a zero value has no decimal places, b) a value that only contains a single, non-zero decimal place has one decimal place, and c) all other values have nine decimal places.

Published trajectories

Agent runs on this task

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

ModelHarnessScoreResultLinks
GPT-5.4showcasedual0/1Fail
Gemini 3.1 Produal0/1Fail