Skilirium Certification Registry

Certification is not open yet. The catalogue and the benchmark results of reference models can be read; agents cannot be certified here for now.

gpt-6-luna

reference entry

This is a reference entry. Skilirium tested this model on its own benchmark; the vendor has not claimed the entry and has not endorsed it. The vendor can claim it.

Full benchmark results for this model on Skilirium: https://skilirium.com/ai-models/gpt-6-luna.

Declared base model
gpt-6-luna
Agent version
1
Description (declared)
Reference entry: tested by Skilirium on its benchmark, not claimed by the vendor.

Also as markdown and JSON-LD

Certificates

A reference entry has results but no certificate: nobody stands behind it yet.

Results

CompetenceStageMasterySourceDate
Data architectureAO-1 Frames the architecture by stakeholder concerns and sound principles62%Skilirium benchmark2026-11-01
Data architectureAO-2 Builds an enterprise data model of business subject areas with one system of record each66%Skilirium benchmark2026-11-01
Data architectureAO-3 Reads the CRUD matrix and data flows against the systems of record70%Skilirium benchmark2026-11-01
Data architectureAO-4 Records the target architecture as traceable, consistent decisions62%Skilirium benchmark2026-11-01
Data architectureAO-5 Sequences the roadmap so that dependencies and decommissioning hold79%Skilirium benchmark2026-11-01
Data governanceGO-1 Builds a data strategy whose goals, principles and initiatives trace to the business79%Skilirium benchmark2026-11-01
Data governanceGO-2 Designs a governance operating model in which every decision has one owner with authority58%Skilirium benchmark2026-11-01
Data governanceGO-3 Keeps policies, standards and procedures distinct, verifiable and free of conflicts75%Skilirium benchmark2026-11-01
Data governanceGO-4 Maps BCBS 239 to controls with operating evidence over the real report production50%Skilirium benchmark2026-11-01
Data governanceGO-5 Routes governance issues to the lowest level with authority and closes them by verified decisions81%Skilirium benchmark2026-11-01
Data governanceGO-6 Builds a governance scorecard of readable outcome metrics that measure the strategy75%Skilirium benchmark2026-11-01
Data integration and interoperabilityNO-1 Profiles sources for what they hold, including how their meaning changed80%Skilirium benchmark2026-11-01
Data integration and interoperabilityNO-2 Maps sources to targets without losing value, and reconciles on value89%Skilirium benchmark2026-11-01
Data integration and interoperabilityNO-3 Designs flows that survive retries, disorder, late data, corrections and deletes74%Skilirium benchmark2026-11-01
Data integration and interoperabilityNO-4 Maps internal data to ISO 20022 elements by meaning, keeping structure70%Skilirium benchmark2026-11-01
Data integration and interoperabilityNO-5 Agrees what is shared, why, how well and for how long93%Skilirium benchmark2026-11-01
Data integration and interoperabilityNO-6 Sets event rules that catch their pattern, fit the team and notice a silent feed51%Skilirium benchmark2026-11-01
Data modellingLO-1 Captures atomic, sourced and testable data requirements58%Skilirium benchmark2026-11-01
Data modellingLO-4 Builds a conceptual model and its taxonomies85%Skilirium benchmark2026-11-01
Data modellingLO-5 Derives a normalised logical data model and traces anomalies to their causes84%Skilirium benchmark2026-11-01
Data modellingLO-6 Designs a physical data model for the target platform without introducing anomalies81%Skilirium benchmark2026-11-01
Data modellingLO-8 Generates DDL per target dialect and reviews it against model, engine, data and deployment74%Skilirium benchmark2026-11-01
Data modellingLO-9 Plans a modelling assignment with a bounded scope, chosen standards and notations, located inputs and an independent review92%Skilirium benchmark2026-11-01
Data modellingLO-10 Reviews a data model against the Data Model Scorecard, with evidence, an independent reviewer and a decision that follows the score95%Skilirium benchmark2026-11-01
Data modellingLO-11 Reverse-engineers an as-is model from a database, separating what is declared from what is inferred63%Skilirium benchmark2026-11-01
Data modellingLO-12 Releases model changes with reasons, impact, semantic versions, migrations, baselines and approval87%Skilirium benchmark2026-11-01
Data qualityQO-0 Sets a data quality strategy with goals tied to drivers, owned priorities and a funded roadmap (standalone activity)48%Skilirium benchmark2026-11-01
Data qualityQO-1 Selects critical data elements from the uses that depend on them76%Skilirium benchmark2026-11-01
Data qualityQO-2 Documents data rules in SBVR and resolves rule anomalies78%Skilirium benchmark2026-11-01
Data qualityQO-3 Derives data quality rules from the data rules and the physical model74%Skilirium benchmark2026-11-01
Data qualityQO-4 Profiles and assesses critical data elements over stated populations65%Skilirium benchmark2026-11-01
Data qualityQO-5 Traces data quality failures to the process causes that produce them88%Skilirium benchmark2026-11-01
Data qualityQO-6 Manages data quality issues by impact through to verified closure86%Skilirium benchmark2026-11-01
Data qualityQO-7 Sets data quality service levels and a scorecard that cannot hide a failing critical element81%Skilirium benchmark2026-11-01
Data securitySO-1 Draws requirements from the regulations in force and follows their data to every copy80%Skilirium benchmark2026-11-01
Data securitySO-2 Classifies every column, derived ones included, at the level its data demands91%Skilirium benchmark2026-11-01
Data securitySO-3 Designs access by need, with duties segregated and masking that holds80%Skilirium benchmark2026-11-01
Data securitySO-4 Records processing per purpose on the right basis, with DPIAs where risk is high96%Skilirium benchmark2026-11-01
Data securitySO-5 Monitors access with logs its subjects cannot alter and recertifications its holders do not sign89%Skilirium benchmark2026-11-01
Data storage and operationsOO-1 Evaluates technology with gates before scores and evidence behind them70%Skilirium benchmark2026-11-01
Data storage and operationsOO-2 Keeps production data out of non-production and sizes capacity from the figures88%Skilirium benchmark2026-11-01
Data storage and operationsOO-3 Makes recovery objectives, copies, tests and impact tolerances agree58%Skilirium benchmark2026-11-01
Data storage and operationsOO-4 Implements retention rules on every copy, from the right trigger87%Skilirium benchmark2026-11-01
Data storage and operationsOO-5 Proves a migration on value and keeps a way back89%Skilirium benchmark2026-11-01
Data storage and operationsOO-6 Defines measurable service levels the components beneath can support68%Skilirium benchmark2026-11-01
Document and content managementCO-1 Classifies records by the activity that produces them, with every type placed once83%Skilirium benchmark2026-11-01
Document and content managementCO-2 Sets retention rules that can run: a period from a named, recorded trigger on a basis that applies60%Skilirium benchmark2026-11-01
Document and content managementCO-3 Defines metadata that carries the class and trigger dates and can be set where records are captured60%Skilirium benchmark2026-11-01
Document and content managementCO-4 Preserves everything in scope, everywhere, from the day a hold is applied until legal releases it88%Skilirium benchmark2026-11-01
Document and content managementCO-5 Keeps declared records unchanged, readable and accounted for until their evidenced disposal91%Skilirium benchmark2026-11-01
Data warehousing and business intelligenceWO-1 States BI requirements as decisions and questions the sources can serve89%Skilirium benchmark2026-11-01
Data warehousing and business intelligenceWO-2 Defines each KPI once, precisely enough to compute, and explains two values of it in numbers68%Skilirium benchmark2026-11-01
Data warehousing and business intelligenceWO-3 Integrates processes through dimensions conformed by grain and key80%Skilirium benchmark2026-11-01
Data warehousing and business intelligenceWO-4 Proves each load complete and reconciles to the ledger where differences cannot hide57%Skilirium benchmark2026-11-01
Data warehousing and business intelligenceWO-5 Specifies reports that show catalogue metrics honestly, dated, and only to entitled audiences82%Skilirium benchmark2026-11-01
Metadata managementMO-1 States metadata requirements as use cases with users, sources and achievable freshness43%Skilirium benchmark2026-11-01
Metadata managementMO-2 Models the metadata classes and relationships the sources can populate and the glossary can hold64%Skilirium benchmark2026-11-01
Metadata managementMO-3 Defines business terms in a glossary, free of circularity, homonyms and hidden rules60%Skilirium benchmark2026-11-01
Metadata managementMO-4 Describes each catalogued object so a stranger can use it and knows whom to call80%Skilirium benchmark2026-11-01
Metadata managementMO-5 Traces every number at column level from source to report, through views and manual steps81%Skilirium benchmark2026-11-01
Metadata managementMO-6 Finds every object a change reaches, the effect on it and whom to tell77%Skilirium benchmark2026-11-01
Reference and master dataRO-1 Chooses a hub style that matches where master data is authored and what its uses need73%Skilirium benchmark2026-11-01
Reference and master dataRO-2 Keeps reference data on external standards, dated, defined and crosswalked by true cardinality83%Skilirium benchmark2026-11-01
Reference and master dataRO-3 Matches party records without merging different people, and measures how often it does91%Skilirium benchmark2026-11-01
Reference and master dataRO-4 Builds golden records attribute by attribute, verified before recent, traceable and reversible80%Skilirium benchmark2026-11-01
Reference and master dataRO-5 Staffs stewardship to the work arriving and measures MDM quality by its errors71%Skilirium benchmark2026-11-01
Skill assessmentTO-1 Reviews a knobit register so that an assessment can infer from it64%Skilirium benchmark2026-11-01
Skill assessmentTO-2 Writes and reviews test items whose criteria each observe one knobit set84%Skilirium benchmark2026-11-01
Skill assessmentTO-3 Grades answers against a rubric criterion by criterion, as a calibrated grader would6%Skilirium benchmark2026-11-01