Public evaluation spaces

Public evaluation spaces — curated bundles of model + dataset + scoring config, browsable without signup.

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

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

• Concept: Evaluation spaces

• Models catalog

• Public evaluations