Raycaster / evalsBack to SpreadsheetBench

SpreadsheetBench

55427

0/1Fail

SpreadsheetBench task 55427. Inspect the exact spreadsheet prompt, compare published model runs, open the agent response trace, and review grades for workbook editing.

Spreadsheet editingDual harness
ssb-55427
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): Compiled and located schools da'!B2:B1461 Expected answer sheet(s): Task: I am attempting to consolidate data about schools from multiple spreadsheets using INDEX and MATCH functions. Specifically, I'm using the formula =INDEX('URN lookup'!$D$2:$D$1461,MATCH(L2,'URN lookup'!$K$2:$K$1461,0)) to look up a DFES number which is located in Column B of the attached 'School data.xlsx', by matching values from column L. However, this formula is not yielding the correct results, and I'm unsure why it is failing. Furthermore, I want to merge additional data that includes a Unique Reference Number (URN) for each school, along with another 15 columns of data. I need help figuring out the issue with my current formula to be able to proceed with merging the rest of the data.

Published trajectories

Agent runs on this task

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

ModelHarnessScoreResultLinks
GPT-5.4showcasedual0/1Fail
Gemini 3.1 Produal1/1Pass