Skip to content

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).

Run this on another model

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.ⓘ

Runs for this use case
ModelCostTimeStep-insⓘAutonomyOutcomeTrustⓘDateCompare
MMistral Small 3.2 24B Instruct (Venice)thinking on$0.001555s0Fully autonomousfailTrust 80%2026-10-30
AClaude Opus 5.5default · thinking on$0.1627s0Fully autonomouspassTrust 80%2026-10-20
AClaude Haiku 5.5default · thinking on$0.005818s0Fully autonomouspassTrust 80%2026-10-20
AClaude Sonnet 5.5default · thinking on$0.0613s0Fully autonomouspassTrust 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.

UseCaseRank badge for Compute final course grades with late penalties, a dropped homework and excused items

Get new runs and ranking changes weekly

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