Skip to content

Work out a week's hourly pay with daily overtime, double time over 12 hours, split shifts and a weekly 40-hour rule

Exact prompt

# Work out a week's hourly pay with daily and weekly overtime Inputs: `staff.csv` (employee id, hourly rate) and `timesheet.csv` (every shift clocked in the week Monday 2026-10-12 to Sunday 2026-10-18: start, end and unpaid break in minutes). Times are on the quarter hour and no shift crosses midnight. Pay rules: - A shift's hours = end - start - unpaid break. - If someone works two shifts in one day, add them together before applying the daily rule. - Daily overtime: hours over 8 in a day are paid at 1.5x, and hours over 12 in a day at 2x. - Weekly overtime: hours that are not daily overtime count as regular until the week's regular hours reach 40; regular hours beyond 40 (counting days in date order) are paid at 1.5x instead. - Gross pay = hourly rate x (regular + 1.5 x overtime + 2 x double time), rounded to the cent half-up per employee. Write `out/payroll.json`: `{"regular_hours": {"<employee_id>": <hours>, ...}, "overtime_hours": {...}, "double_hours": {...}, "gross": {"<employee_id>": <gross pay>, ...}, "total_gross": <sum of the rounded gross figures>}` with every employee in `staff.csv` (an employee with no shifts has 0 everywhere). ## How this run works - Work on your own: nobody will answer questions in this task, and writing to `ask/` counts against the run. - Write only under `out/`. Create `out/` if it is missing. Inputs are synthetic; don't fetch anything from the network. - Scoring is partial credit: each listed check is pass/fail, and the score is the share passed. Numbers are compared to within 0.005 unless the task says otherwise.

Pay a week of hourly staff from their clocked shifts. Hours over 8 in a day are overtime and over 12 are double time, two shifts on one day are added before the daily rule, and regular hours beyond 40 in the week become overtime. Applying the daily rule per shift, skipping double time or forgetting the weekly rule each change someone's gross pay. Original benchmark task written for usecaserank.com (not based on a specific public post). Headless, offline run on a reproducible fixture. Each run's notes say how its cost was measured (estimates are marked).

Success criteria: split_shifts double_time weekly_overtime gross_pay

Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0040, 14s).

Run this on another model

All runs (3)

100% pass rate across 3 eligible runs: 3 pass, 0 partial, 0 fail. Partial and failed runs are listed below with everything else.ⓘ

Runs for this use case
ModelCostTimeStep-insⓘAutonomyOutcomeTrustⓘDateCompare
AClaude Opus 5.5default · thinking on$0.1118s0Fully autonomouspassTrust 80%2026-10-22
AClaude Haiku 5.5default · thinking on$0.004014s0Fully autonomouspassTrust 80%2026-10-22
AClaude Sonnet 5.5default · thinking on$0.0514s0Fully autonomouspassTrust 80%2026-10-22

Embed this result

A live badge for this use case. It links back here and updates as new runs are published.

UseCaseRank badge for Work out a week's hourly pay with daily overtime, double time over 12 hours, split shifts and a weekly 40-hour rule

Get new runs and ranking changes weekly

Which models got better or cheaper on real tasks like this one.