Tasks · desk · Bookkeeping
Allocate August overhead to departments
shared-cost-allocation · timeout 1200 s · source
The ask
Sent verbatim as the prompt. The agent works in a copy of the workspace below and sees nothing else.
Please do the August overhead allocation to the departments. Carla's memo explains the new way she wants it done. Save it as allocation.xlsx.
Workspace
- gl_detail_overhead_2026-08.csv
- headcount_and_floorplan.xlsx
- memo_overhead_allocation.txt
- overhead_allocation_2026-07.xlsx
Expected deliverables
- allocation.xlsx
This task also has a task-specific grader (check.py).
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 formula errors | xlsx_no_errors | yes | 0 |
| every account splits to the cent | custom | yes | 0 |
| grand total allocated | xlsx_value_present | yes | 0 |
| Mill Shop total | xlsx_value_present | yes | 0 |
| Finishing total | xlsx_value_present | yes | 0 |
| Install total | xlsx_value_present | yes | 0 |
| Showroom total | xlsx_value_present | yes | 0 |
| Admin total | 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 | 4.2 | 0.0711 | |
| Codex / GPT-5.6 sol | 3 | 3 | 5.1 | 0.5216 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "shared-cost-allocation".