# Scorers

{% hint style="info" %}
**Available in Stratix Premium.** Scorers are a logged-in workspace feature at [stratix.layerlens.ai](https://stratix.layerlens.ai). Stratix Public users can browse the catalog but not author or run scorers.
{% endhint %}

## Scorers

Scorers are **LLM-backed graders** — a model plus an evaluation prompt — that you apply across benchmarks. Your org builds a library of them over time.

URL: [`stratix.layerlens.ai/dashboard/scorers`](https://stratix.layerlens.ai/dashboard/scorers)

### Anatomy

A scorer record contains:

* **Name** (3–64 chars) and **description** (10–500 chars)
* **Model** — the LLM that runs the prompt (pick from the catalog or a BYOK model)
* **Prompt** — the evaluation instructions

Scorers are **immutable** once created. To revise a rubric, author a new scorer; this keeps prior evaluation results reproducible against the exact rubric that produced them.

### When to use a scorer vs a judge

* **Scorer** — reusable rubric applied as part of a benchmark or custom-dataset evaluation. Immutable. No versioning, no trace-level surface.
* **Judge** — versioned rubric tuned with labeled examples, applied to traces (and optionally to evaluation runs). Use a [judge](/8.-evaluate-score-the-outputs/judges.md) when you need GEPA tuning or trace-level evaluation.

### Creating a scorer

Click **New scorer**:

1. **Name and description** — the catalog labels.
2. **Pick a model** — frontier for nuanced rubrics; cost-optimized for high-volume, narrow rubrics.
3. **Author the prompt** — include input-variable placeholders (`{{output}}`, `{{expected}}`, `{{context}}`, `{{input}}` as relevant) and tell the model exactly what to return (numeric range, label set, structured JSON).
4. **Test on examples** — paste sample inputs/outputs, verify the scorer returns expected verdicts.
5. **Save** — scorer becomes available in any evaluation in your org.

### Scorers in evaluations

When you create an evaluation, the scoring step lets you stack any number of scorers. Each scorer produces a per-row verdict; the evaluation's overall score is configurable (mean, median, all-pass, etc.).

### Deterministic / code graders

Some checks are inherently deterministic — exact match, regex, JSON-schema validity, Flesch-Kincaid grade, fairness math. These don't fit the LLM-prompt Scorer surface and run as separate **code graders** in the evaluation runtime. See [Custom code grader recipe](https://github.com/LayerLens/gitbook-full/blob/main/08-evaluate/cookbook/custom-code-scorer.md).

### Where to next

* [Concept: Scorers](/8.-evaluate-score-the-outputs/scorers-1.md)
* [Judges](/8.-evaluate-score-the-outputs/judges.md)
* [Evaluations](/8.-evaluate-score-the-outputs/evaluations.md)
* [SDK reference — Scorers](/8.-evaluate-score-the-outputs/scorers.md)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.layerlens.ai/8.-evaluate-score-the-outputs/scorers.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.