Tasks · desk · Bookkeeping
West Gallery budget burn for the capital committee
project-budget-burn · timeout 1800 s · source
The ask
Sent verbatim as the prompt. The agent works in a copy of the workspace below and sees nothing else.
Alma needs the West Gallery budget burn for the capital committee - where each cost code stands. Her email explains how she counts it. Save it as burn.xlsx.
Workspace
- ap_invoices_project_WG-26.csv
- change_order_log.xlsx
- email_from_director.txt
- purchase_orders_west_gallery.csv
- west_gallery_budget_board_approved.xlsx
Expected deliverables
- burn.xlsx
Checks
The task passes only when every required check passes. Reference answers, tolerances, and the planted traps are in the repository, not here.
| Check | Type | Required | Failed (frozen) / 6 |
|---|---|---|---|
| live formulas | xlsx_has_formulas | yes | 0 |
| no error cells | xlsx_no_errors | yes | 0 |
| exhibit fabrication committed | xlsx_value_present | yes | 0 |
| HVAC remaining | xlsx_value_present | yes | 0 |
| electrical remaining | xlsx_value_present | yes | 0 |
| gallery lighting spent | xlsx_value_present | yes | 0 |
| design fees spent | xlsx_value_present | yes | 0 |
| total committed | xlsx_value_present | yes | 0 |
| total remaining | xlsx_value_present | yes | 0 |
Recorded results, complete desk comparison
pass pass, frozen scorer only fail timed out
| System | Repetitions | Frozen / 3 | Raw / 3 | Median minutes | Mean cost (USD) |
|---|---|---|---|---|---|
| Proto / DeepSeek V4.1 Flash | 3 | 3 | 6.3 | 0.1054 | |
| Codex / GPT-5.6 sol | 3 | 3 | 6.1 | 0.7655 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "project-budget-burn".