Rate a courier firm's shipments with dimensional weight, zone bands, a minimum charge, a weekly fuel surcharge and residential fees
Exact prompt
# Rate a courier firm's shipments with dimensional weight, zone bands, a minimum charge, a weekly fuel surcharge and residential fees Inputs: `shipments.csv` (awb, account, from_zone, to_zone, service, weight_kg, length_cm, width_cm, height_cm, residential, ship_date), `zones.json` (band for each zone pair, listed once in either order), `rates.json` (per service and band: base, per_half_kg) and `surcharges.json` (dim_divisor, min_charge, residential_fee, fuel: list of {week_start, pct}). All accounts and parcels are synthetic; amounts are in dollars. These rules are the firm's policy; where `ops-note.txt` disagrees, the rules win. Rules: - Billable weight: dimensional weight = length_cm × width_cm × height_cm / dim_divisor. Billable weight is the larger of weight_kg and dimensional weight, rounded up to the next 0.5 kg. - Transport: look up the band for the zone pair (A-B is the same pair as B-A). Transport = base + per_half_kg × the number of half kilos of billable weight above 1 kg, and never less than min_charge. - Fuel: use the pct of the fuel row whose week_start (a Monday) begins the week containing ship_date. Fuel = pct percent of transport, rounded half-up to the cent. The residential fee is not fuel-surcharged. - Residential: add residential_fee when residential is yes. Shipment total = transport + fuel + residential fee. - Write `out/rated.json`: `{"shipments": {"<awb>": {"billable_kg": <number>, "transport": <dollars>, "fuel": <dollars>, "residential": <dollars>, "total": <dollars>}, ...}, "accounts": {"<account>": <sum of totals>, ...}}`. ## 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.
Rate a synthetic courier firm's shipments. Billable weight is the larger of scale and dimensional weight rounded up to the half kilo, zone pairs are listed in either order, transport has a minimum charge, the fuel surcharge changes by week and applies only to transport, and residential deliveries carry a flat fee. An ops note gets the weight, rounding and fuel rules wrong. 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: billable_weight zone_transport fuel_week shipment_totals account_totals
Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0047, 16s).
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.ⓘ
| Model | Cost | Time | Step-insⓘ | Autonomy | Outcome | Trustⓘ | Date | Compare |
|---|---|---|---|---|---|---|---|---|
| AClaude Opus 5.5default · thinking on | $0.12 | 1m | 0 | Fully autonomous | pass | Trust 80% | 2026-10-25 | |
| AClaude Haiku 5.5default · thinking on | $0.0047 | 16s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-25 | |
| AClaude Sonnet 5.5default · thinking on | $0.06 | 16s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-24 |
Embed this result
A live badge for this use case. It links back here and updates as new runs are published.
Get new runs and ranking changes weekly
Which models got better or cheaper on real tasks like this one.