Your OpenVals roadmap
OpenVals is the trust layer for AI. Use this docs set as a map: start with why it exists, run your first evaluation, learn the trust metrics, then move into platform workflows, integrations, and enterprise readiness.
The question OpenVals answersCan you trust this model for this use case?
What OpenVals does
Traditional benchmarks stop at accuracy. OpenVals measures the signals that matter before production: correctness, factuality, hallucination risk, reliability, safety, latency, dataset quality, and decision readiness.
The learning path
Follow these steps in order the first time. Jump ahead later once you know which layer you need.
See why demo accuracy fails in production, and what trust questions every team should ask.
Read Why OpenValsGet OpenVals on your machine so you can run evaluations locally and inspect your environment.
Install OpenValsBenchmark a model, validate a dataset, and produce a trust report in minutes.
Start first evaluationDRS, factuality, hallucination probability, reliability, and how to interpret a good vs risky score.
Open DRS guideRun multi-model benchmarks across finance, software, cybersecurity, healthcare, and more.
Explore benchmarkingConnect providers, run Use Case Advisor, launch validation runs, and read evidence packs.
Open platform guideUse AIxLence when you need capability diagnosis, roadmap sequencing, and board-ready outputs.
Open AIxLence docsPick your starting lane
Install, run benchmarks, validate datasets, and inspect CLI samples.
Start with installIntegrations, Use Case Advisor, validation runs, and end-to-end user flow.
Start with integrationsDRS, reporting, domains, and AIxLence readiness for decision evidence.
Start with reportingWhat you will learn to measure
| Area | What you get | Go to |
|---|---|---|
| Trust score | Decision Reliability Score across key signals | DRS |
| Correctness | Model evaluation and factuality checks | Model evaluation |
| Hallucination risk | Probability bands and failure modes | HPI |
| Data quality | Schema, balance, and dataset health | Dataset intelligence |
| Comparison | Multi-model ranking on real domains | Benchmarking |
| Evidence | Executive reports and UI previews | Reporting |
Go deeper when you need it
- API contracts and architecture → Platform API Spec and Architecture Flow
- Domain datasets → Supported Benchmark Domains
- Security / contribution norms → Security Policy and Contributing
- Product direction → Product roadmap and Vision
Prefer a guided first hour? Start with Why OpenVals, then Install, then First evaluation.