LayerLens Stratix Documentation
Welcome to LayerLens Stratix documentation. Three customer-facing experiences, one platform — pick a path and ship faster.
LayerLens Stratix is the AI evaluation platform for teams that need to know — before customers do — whether a model, prompt, or agent is good enough to ship. Browse the world's largest public catalog of model evaluations, run private evaluations on your own data, score traces with deterministic rules and LLM judges, and ship AI you can trust.
Recent updates
System judges shipped — a curated set of platform-maintained LLM judges for quality, safety, and policy, ready to run with no setup.
SDK v1.3.0 —
client.judge_optimizations(GEPA) and trace-set filtering onclient.trace_evaluations.create.
Three customer-facing experiences
stratix.layerlens.ai — anonymous browsing of 175+ models, 52+ benchmarks, and 2,000+ public evaluations. Compare any two models head-to-head. No sign-up required.
stratix.layerlens.ai — after you sign in. The logged-in workspace where teams run private evaluations, build judges, score traces, manage scorers, run agentic evaluations, and govern AI quality across an organization.
pip install layerlens --extra-index-url https://sdk.layerlens.ai/package — the Python client SDK (v1.3.0) for programmatic evaluation, judge orchestration, and trace ingestion. 138 sample programs.
Pick a path
I'm a researcher
Explore 175+ models against 52+ benchmarks, browse 2,000+ public evaluations.
I'm an admin or buyer
Set up your org, manage seats and credits, evaluate enterprise readiness.
The Stratix Workflow
Five stages from raw model to governed production. Every Premium capability maps to one of them.
Select → Build → Observe → Evaluate → Improve. This is the spine. Every concept, how-to, tutorial, and recipe in this documentation pins to one of these stages. Learn the workflow →
What's new
Q1 2026 model leaderboard — refreshed quarterly with GPT-5.3, Claude Opus 4.6, Gemini 3.1 Pro/Flash, and 200+ more.
Agentic evaluations — pre- and post-deployment quality gates for multi-step agents. Read the announcement.
GEPA judge optimization — automatically tune your LLM judges against ground-truth labels. Read the concept.
Need help?
In-app: click the Assistant icon (Premium only) for context-aware help.
Email: [email protected]
Docs feedback: open an issue or reach out via the in-app feedback form.
Where to next
New here? → What is LayerLens Stratix?
Want to ship today? → Getting Started
Researching for purchase? → How Stratix compares
Building a business case? → Pricing
Last updated
Was this helpful?
