Tasks · desk · Bookkeeping
August bank reconciliation for the checking account
bank-reconciliation · 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.
Can you do the August bank reconciliation for our checking account? The bank export, the ledger and Alma's July rec are in the folder, and Dean's email says what he wants. Save it as reconciliation.xlsx.
Workspace
- bank_rec_2026-07.xlsx
- email_from_dean.txt
- gl_1010_checking_2026-08.xlsx
- harbor_trust_checking_2026-08.csv
Expected deliverables
- reconciliation.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 |
|---|---|---|---|
| reconciliation.xlsx exists | file_exists | yes | 0 |
| live formulas | xlsx_has_formulas | yes | 0 |
| no error cells | xlsx_no_errors | yes | 0 |
| outstanding checks and deposits in transit totals | custom | yes | 0 |
| adjusted balance | xlsx_value_present | yes | 1 |
| both sides tie and items listed | custom | yes | 1 |
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 | 2 | 2 | 8.4 | 0.1081 | |
| Codex / GPT-5.6 sol | 3 | 3 | 5.4 | 0.6420 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "bank-reconciliation".