Tasks · desk · Spreadsheet
Sales tax on each September order
sales-tax-by-address · 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.
I need the sales tax worked out on each of this month's orders before I invoice them. Use the accountants' rate table and save orders_tax.csv - my note has the rest.
Workspace
- note_from_carmen.txt
- orders_2026-09-01_to_2026-09-12.csv
- sales_tax_table_2026.xlsx
Expected deliverables
- orders_tax.csv
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 |
|---|---|---|---|
| requested columns | csv_columns | yes | 0 |
| every order | csv_set_equal | yes | 0 |
| row count | csv_row_count | yes | 0 |
| tax per order | csv_values_match | yes | 0 |
| rate per order | custom | 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 | 1.2 | 0.0162 | |
| Codex / GPT-5.6 sol | 3 | 3 | 2.7 | 0.2847 |
Per-attempt check verdicts, raw and frozen verdicts, usage, receipt and artifact hashes for this task are in results/latest/attempts.jsonl under "task": "sales-tax-by-address".