Tasks · desk · Extraction
Expense table from scanned trip receipts
receipts-scanned · 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.
Dana scanned all her Denver trip receipts. Please turn them into expenses.csv for reimbursement - finance's instructions and template are in the folder.
Workspace
- denver_trip_receipts/IMG_4410.pdf
- denver_trip_receipts/IMG_4413.pdf
- denver_trip_receipts/IMG_4416.pdf
- denver_trip_receipts/IMG_4419.pdf
- denver_trip_receipts/IMG_4422.pdf
- denver_trip_receipts/IMG_4425.pdf
- denver_trip_receipts/IMG_4428.pdf
- denver_trip_receipts/IMG_4431.pdf
- denver_trip_receipts/IMG_4434.pdf
- denver_trip_receipts/IMG_4437.pdf
- denver_trip_receipts/IMG_4440.pdf
- denver_trip_receipts/IMG_4443.pdf
- expense_report_template.csv
- finance_expense_instructions.txt
- note_from_dana.txt
Expected deliverables
- expenses.csv
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 |
|---|---|---|---|
| template columns | csv_columns | yes | 0 |
| one row per receipt | csv_set_equal | yes | 0 |
| row count | csv_row_count | yes | 0 |
| merchants | csv_values_match | yes | 0 |
| dates | csv_values_match | yes | 0 |
| subtotals and tax | csv_values_match | yes | 0 |
| tips and totals | csv_values_match | 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 | 12.7 | 0.0784 | |
| Codex / GPT-5.6 sol | 3 | 3 | 1.7 | 0.3381 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "receipts-scanned".