Raycaster / evalsTask overviewSpreadsheetBenchCategory

SpreadsheetBench · Gemini 3.1 Pro · dual

534-26

0/1Fail

Gemini 3.1 Pro on SpreadsheetBench: 534-26 (dual harness). Browse score, rubric, and public trace.

0/1 · Fail
SpreadsheetBench
AI Agents for Spreadsheet Automation and Workbook Editing

Prompt excerpt

Task context

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): A1:AQ1 Expected answer region(s): 'Sheet1'!I1:AQ1 Expected answer sheet(s): Sheet1 Task: How can I write a macro that will delete the entire column in an Excel sheet if the Date value in the column is earlier than the current month and year?

Response trace

Agent response, tools, files, and edits

Open full trace

On mobile, open the full trace for the best view of the agent response, tool calls, file reads, edits, and grading context.

Open mobile trace