Work out arrival times, layovers and tight connections for a multi-leg trip across time zones
Exact prompt
# Work out a multi-leg trip itinerary across time zones Input: `itinerary.json`, a list of flight legs in travel order. Each leg has a local departure time (`depart_local`, wall-clock time at the departure airport), the departure and arrival time zones (IANA names) and the block time in minutes. Rules: - Arrival time = departure instant + duration_min, written as wall-clock time in the arrival airport's zone, format `YYYY-MM-DDTHH:MM`. - Use the real time-zone rules for the travel dates, including daylight-saving changes. - Layover = minutes from a leg's arrival to the next leg's departure (real elapsed minutes). - A connection is tight when its layover is under 60 minutes. - total_elapsed_min = real minutes from the first departure to the last arrival. - date_change_legs = the legs whose local arrival date differs from their local departure date, in travel order. Write `out/itinerary.json`: `{"arrivals": {"<leg>": "<YYYY-MM-DDTHH:MM>", ...}, "layovers_min": {"<leg>": <int>, ...}, "tight": [<leg>, ...], "total_elapsed_min": <int>, "date_change_legs": [<leg>, ...]}` `layovers_min` and `tight` are keyed by the leg that arrives before the connection (every leg except the last), and `tight` is in travel order. ## 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.
Turn 4-6 flight legs given in local departure times and block minutes into local arrival times, layovers, tight-connection flags, total trip time and date-change legs. The travel window spans the late-October and early-November daylight-saving changes, and routes include half-hour and 45-minute offset zones. Departures that fall on ambiguous or skipped local times are redrawn. 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: arrival_local_times dst_rules_applied layover_minutes tight_connections total_elapsed date_change_legs
Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0034, 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 | $0.0045 | 1m | 0 | Fully autonomous | fail | Trust 80% | 2026-10-28 | |
| AClaude Opus 5.5default · thinking on | $0.11 | 16s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-20 | |
| AClaude Haiku 5.5default · thinking on | $0.0034 | 13s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-20 | |
| AClaude Sonnet 5.5default · thinking on | $0.05 | 12s | 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.