Compute final course grades with late penalties, a dropped homework and excused items
Exact prompt
# Compute final course grades from a gradebook Inputs: `syllabus.json` (category weights, letter cut-offs, late rule) and `gradebook.json` (each student's scores per assignment: points earned, points possible, days late, or "EX" for excused). Rules: - Excused ("EX") items are left out of both earned and possible points. - Late homework loses 10% of its earned points per day late, up to 3 days (so at most 30%). Only homework has a late penalty. - Drop each student's single lowest homework, by percentage of possible points after the late penalty (on a tie, drop the earlier one). Excused items can't be dropped. - Category percentage = sum of earned points / sum of possible points x 100, using the remaining items. - Final percentage = sum of category percentage x category weight, rounded half-up to 2 decimal places. - Letter grade comes from the rounded final percentage and the cut-offs in syllabus.json (a cut-off is a minimum, inclusive). Write `out/grades.json`: `{"<student_id>": {"homework_pct": <number>, "quiz_pct": <number>, "exam_pct": <number>, "final_pct": <number>, "letter": "<A-F>"}, ...}`. Category percentages are checked to within 0.01. ## 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 category percentages, weighted final percentages and letter grades for 10-14 students. The rules cover a capped per-day late penalty, dropping the lowest homework by percentage, and excused items that count toward neither earned nor possible points. Finals within 0.3 points of a letter cut-off or near a rounding tie 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: homework_with_late_and_drop quiz_excused_excluded exam_pct final_pct letters late_penalty_capped
Best model for this task so far: Claude Haiku 5.5 (effort default (no --effort flag) · thinking on) (success, $0.0058, 18s).
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 | $0.0015 | 55s | 0 | Fully autonomous | fail | Trust 80% | 2026-10-30 | |
| AClaude Opus 5.5default · thinking on | $0.16 | 27s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-20 | |
| AClaude Haiku 5.5default · thinking on | $0.0058 | 18s | 0 | Fully autonomous | pass | Trust 80% | 2026-10-20 | |
| AClaude Sonnet 5.5default · thinking on | $0.06 | 13s | 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.