Skip to main content

​
Scoring Rubrics

Gradient’s default rubric (v5) evaluates candidates across five categories (Correctness, Deliverable Quality, Reflection Quality, AI Fluency, Prioritized Skills) totaling 100 points. Gradient builds the rubric for each assessment. See Scoring for what each category measures.

​
Default rubric

The overall score out of 100 is a weighted blend of the five categories. The category weights are fixed by the rubric version; Gradient sets the sub-criteria inside each category. Each category contains sub-criteria. Every sub-criterion carries a point value, a short description, and a 0-4 anchored scale (its anchors) that defines what each score from 0 to 4 means. The anchors are the scale the judge actually grades against, and they are what calibration reads and sharpens.
AI Fluency is locked. Gradient manages it centrally. It cannot be edited or reweighted.

​
Who sets the rubric

Gradient writes the rubric for each assessment when it builds the assessment. You cannot edit the rubric. If you want a different rubric, email hi@trygradient.ai. You can still read the rubric on the assessment page, and you can sharpen it through calibration.

​
Anchored 0-4 scales

Every sub-criterion should carry an anchors ladder: five descriptors, one for each score from 0 to 4, where 0 is absent or nothing and 4 is exceptional. Gradient writes them.
The anchors are not decoration. They matter in two ways:
  • They are the scoring scale. The judge grades a sub-criterion against its anchor descriptors, not its one-line description. The description frames the criterion; the anchors define what each level actually means. A criterion with vague or missing anchors produces vague scores.
  • They are what calibration tunes. When a reviewer grades a candidate on the 0-4 ladder and disagrees with the AI, calibration sharpens these anchor descriptors so future scoring matches your standard. A sub-criterion with no anchors cannot be calibrated, because there is no ladder to sharpen.

​
Scoring methods

Sub-criteria are scored by one of these methods:

Deterministic

Ground-truth checks against known-correct facts and required elements. Used for Correctness.

LLM Judge

An AI evaluator assesses quality against the rubric criteria. Best for subjective qualities like insight and reflection.

Event Analysis

Automated analysis of candidate behavior patterns. Best for measurable actions like whether a figure was verified before use.

Hybrid

Combines approaches. AI Fluency is graded this way, centrally, by Gradient.

​
Tips for reading a rubric

  • Read the anchors. The anchors show what each score from 0 to 4 means for that sub-criterion.
  • Check the points. Sub-criteria with more points have more effect on the total score.
  • Use calibration. When you disagree with a score, grade the candidate yourself. Calibration then sharpens the anchors.
  • Do not try to edit AI Fluency. It is locked.