GitHub-native · no uploads, no zip files
Built at the Syracuse University iSchool Grading IST356 since day one Python · pytest · GitHub-native Sign in with Microsoft
What it does

Three ways to grade — one clear answer

Objective tests, judged nuance, and a human override, combined per rubric case into a score students can actually learn from.

Automated tests

A sandboxed pytest runner scores objective cases the moment a student pushes — no waiting, no ambiguity.

AI-judged criteria

An LLM judge evaluates code style and reflection against your rubric levels — the nuance of a TA, at the speed of a script.

A hint on every point

Every criterion returns specific, actionable advice — "add a colon", "name the error types" — not just a number.

GitHub-native

Students fork the assignment, push their work, and request grading. No uploads, no zip files, real commit history.

Rubrics that run themselves

Define rubric.json once — automated cases, AI judges, and point levels re-apply on every single submission.

You stay in control

Override any AI or human case, add audit notes, and finalize. Automated cases stay locked — grading you can defend.

How it works

Push code. Get feedback.

From a student's first commit to a graded, explained result — usually in minutes.

01

Fork the repo

Students fork the assignment repo from GitHub with one click.

02

Push your work

They commit and push their solution — normal Git, real history.

03

Request grading

One click clones the fork, runs tests, and calls the AI judge.

04

Get specific feedback

Per-criterion score, why, and how to improve — emailed and on-screen.

Who it's for

Grade less. Teach more.

For instructors

Consistent, defensible grading

  • Author the rubric once; it scores every submission the same way.
  • Automated cases handle the objective work — you spend time only where judgment matters.
  • Override AI, leave audit notes, and finalize with a full grading log.
For students

Know exactly why

  • See which tests failed, what the grader saw, and how to fix it.
  • Every point comes with a hint you can act on before the next attempt.
  • Fix, push, and request grading again — feedback is a loop, not a verdict.
The whole idea
Because feedback > grade
A number tells a student where they landed. GRADERTHAN tells them how to move.

Turn your next assignment into feedback

Sign in with your Microsoft account and connect a course. Your rubric does the grading from there.