Pick the cheaper of two carriers per parcel using dimensional weight, zones and oversize fees
Exact prompt
# Pick the cheaper carrier for each parcel Inputs: `parcels.json` (each parcel's length, width and height in inches, weight in pounds, destination zone) and `rates.json` (two carriers' rate cards). Rules, applied per carrier: - Dimensional weight = length x width x height / that carrier's dim_divisor, rounded UP to a whole pound. - Actual weight is rounded UP to a whole pound. - Billable weight = the larger of the rounded actual weight and the dimensional weight. - Price = zone base price (covers the first pound) + per_lb for the zone x (billable weight - 1). - Add the carrier's oversize_fee when the parcel's longest side is over the carrier's oversize_longest_in (strictly greater). - Choose the carrier with the lower price; if both are equal, choose the carrier listed first in rates.json. Write `out/shipping.json`: `{"parcels": {"<parcel_id>": {"billable_lb": {"<carrier>": <int>, ...}, "price_usd": {"<carrier>": <usd>, ...}, "choice": "<carrier>"}, ...}, "total_usd": <sum of chosen prices>}`. ## 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.
Price 10-15 parcels on two carriers' rate cards using dimensional weight with each carrier's own divisor, whole-pound rounding up, zone pricing and an oversize fee above a longest-side threshold, then choose the cheaper carrier per parcel. Parcels exactly at an oversize threshold and exact price ties are redrawn. All prices are whole cents, so no rounding ties arise. 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_weights dimensional_weight_applied prices oversize_fees carrier_choice total
Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0040, 13s).
All runs (4)
75% pass rate across 4 eligible runs: 3 pass, 0 partial, 1 fail. Partial and failed runs are listed below with everything else.ⓘ
| Model | Cost | Time | Step-insⓘ | Autonomy | Outcome | Trustⓘ | Date | Compare |
|---|---|---|---|---|---|---|---|---|
| MMistral Small 3.2 24B Instruct (Venice)thinking on | $0.0009 | 16s | 0 | Fully autonomous | fail | Trust 80% | 2026-10-28 | |
| AClaude Opus 5.5default · thinking on | $0.12 | 15s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-20 | |
| AClaude Haiku 5.5default · thinking on | $0.0040 | 13s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-20 | |
| AClaude Sonnet 5.5default · thinking off | $0.04 | 8s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-20 |
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.