> For the complete documentation index, see [llms.txt](https://docs.layerlens.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.layerlens.ai/5.-select-pick-the-model/models-catalog.md).

# Models catalog

Stratix Public Models catalog — 175+ models with metadata, capability tags, and per-benchmark scores.

The Stratix Public Models catalog is the read-only browse layer over the platform's model catalog. 175+ models, refreshed continuously, with rich metadata and benchmark scores.

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

## What you can see for each model

* **Identity** — provider, model family, version, release date
* **Capabilities** — chat, code, reasoning, vision, embeddings, tool-use
* **Context window** — maximum tokens
* **Modalities** — text, vision, audio
* **Licensing** — proprietary, open-weight (with license name)
* **Pricing** — provider-published per-token cost
* **Per-benchmark scores** — every benchmark this model has been evaluated against
* **Score history** — how the model has performed over time

## Filtering

Sidebar filters:

* Provider (OpenAI, Anthropic, Google, Meta, Mistral, etc.)
* Capability
* Context window (minimum)
* Licensing (proprietary / open-weight)
* Modalities

## Sorting

* Alphabetical
* By score on a chosen benchmark
* By release date (newest first)
* By popularity (view count)

## Searching

Free-text search across model name, provider, and description. Supports operators like `provider:openai` and `capability:code`.

## Per-model page

Each model has a dedicated page with:

* Hero card (name, provider, capabilities)
* Full metadata
* Score table across benchmarks
* Score-history chart
* Public evaluations that included this model
* Quick **Compare** button to compare with another model

## How scores are produced

Scores in the public catalog come from public evaluations run by LayerLens or contributed by partners. Methodology is documented per benchmark on the [benchmarks catalog](/5.-select-pick-the-model/benchmarks-catalog.md). Quarterly research reports add narrative around the trends.

## Where data refreshes from

The model catalog updates as LayerLens runs new public evaluations and as new models are added. Per-model "last updated" timestamps appear on the model page.

## Where to next

* [Compare models](/5.-select-pick-the-model/compare-models.md)
* [Benchmarks catalog](/5.-select-pick-the-model/benchmarks-catalog.md)
* [Public evaluations](/5.-select-pick-the-model/public-evaluations.md)
* [Concept: Models and benchmarks](/5.-select-pick-the-model/models-and-benchmarks.md)