# Public evaluation spaces

An **evaluation space** is a workspace bundling a model selection, a dataset/benchmark selection, and a scoring config. Public spaces are curated by LayerLens and partners — browse them to see how seasoned teams structure evaluations.

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

## What's in a space

* **Model selection** — one or more models being evaluated
* **Dataset / benchmark selection** — what's being evaluated against
* **Scoring config** — which scorers and judges
* **Latest run results** — top-line scores and detail
* **Description and methodology notes** — context for why this space exists

## How to use public spaces

* **Read for inspiration.** A well-structured space is a recipe for "how to evaluate X."
* **Replicate.** Use the same models, the same benchmarks, the same scoring on your own dataset. Premium evaluations let you instantiate a similar configuration.
* **Compare.** Run the same evaluation against your data and see how your results compare to the public space.

## Browse and filter

* Search by name or description
* Filter by capability — code, reasoning, multilingual, etc.
* Filter by industry tag
* Sort by recency or by activity

## Premium evaluation spaces

Premium adds **private spaces** that are scoped to your org. The shape is identical — model + dataset + scoring + results — but visibility is private.

## Where to next

* [Premium — Spaces](/8.-evaluate-score-the-outputs/spaces.md)
* [Concept: Evaluation spaces](/8.-evaluate-score-the-outputs/evaluation-spaces.md)
* [Models catalog](/5.-select-pick-the-model/models-catalog.md)
* [Public evaluations](/5.-select-pick-the-model/public-evaluations.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/5.-select-pick-the-model/public-evaluation-spaces.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.