Skip to content

Build a final league table with abandoned matches, a forfeit, a points deduction and head-to-head tie-breaks

Exact prompt

# Final league table with tie-breaks Inputs: `matches.csv` (every fixture of a double round-robin season, with status) and `sanctions.csv` (points deductions). Produce the final table. - Points: 3 for a win, 1 for a draw, 0 for a loss, minus any deduction in `sanctions.csv`. - An abandoned match doesn't count; its replay is a separate row. A forfeited match counts as a 3-0 win for the other team, whatever score was recorded. - Rank teams by points, then head-to-head points, then goal difference, then goals scored, then team name A to Z. - Head-to-head points = points earned in the matches that count between all the teams level on points (after deductions), with no deductions applied inside it, worked out once for that whole group. Goal difference and goals scored are over the whole season and include forfeits as 3-0. - Report the champion (1st) and the two relegated teams (the bottom two, 2nd-last first). Write `out/standings.json`: `{"table": [<team names, 1st to last>], "points": {"<team>": <points after deductions>}, "goal_difference": {"<team>": <n>}, "champion": "<team>", "relegated": ["<2nd-last>", "<last>"]}`. ## 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.

Compute the final standings of an 8-10 team double round-robin from about 60-90 fixture rows. Abandoned matches have separate replays, one match was forfeited and must count 3-0 whatever was recorded, one club has a points deduction, and teams level on points are separated by head-to-head before goal difference. Counting abandoned games, putting goal difference first, or taking forfeits at face value each moves teams in the table. 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: points table_order abandoned_and_forfeit champion_and_relegation

Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0045, 16s).

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$0.1452s0Fully autonomouspassTrust 80%2026-10-21
AClaude Haiku 5.5default · thinking on$0.004516s0Fully autonomouspassTrust 80%2026-10-21
AClaude Sonnet 5.5default · thinking on$0.0517s0Fully autonomouspassTrust 80%2026-10-21

Embed this result

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

UseCaseRank badge for Build a final league table with abandoned matches, a forfeit, a points deduction and head-to-head tie-breaks

Get new runs and ranking changes weekly

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