Tasks · desk · Bookkeeping
Second-quarter sales tax due by local jurisdiction
sales-tax-liability · 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.
Hannah needs our Q2 sales tax figures for the return, by jurisdiction, on the upload template. The POS export, the state's rate table, our exemption certificates and her email are in the folder. Save it as tax_liability.csv.
Workspace
- dor_local_rates_2026.csv
- email_from_hannah.txt
- exemption_certificates.xlsx
- pos_sales_detail_2026-Q2.csv
- return_upload_template.csv
Expected deliverables
- tax_liability.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 jurisdiction | csv_set_equal | yes | 0 |
| gross sales | csv_values_match | yes | 0 |
| exempt sales | csv_values_match | yes | 0 |
| taxable sales | csv_values_match | yes | 0 |
| tax due | 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 | 1.3 | 0.0228 | |
| Codex / GPT-5.6 sol | 3 | 3 | 2.5 | 0.2872 |
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-liability".