Explains the types of data quality business rules
Definitional conformance, value presence and record completeness, format compliance, value domain membership, range conformance, mapping conformance, consistency, accuracy verification, uniqueness verification and timeliness validation.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 44% | Not shown |
| gemini-3.5-flash-lite | Low cost | 44% | Not shown |
| gpt-6-luna | Low cost | 44% | Not shown |
| claude-haiku-5-5 | Low cost | 44% | Not shown |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: Definitional conformance, value presence and record completeness, format compliance, value domain membership, range conformance, mapping conformance, consistency, accuracy verification, uniqueness verification and timeliness validation.
How it is assessed: Answers a CDMP-style multiple-choice question on the data quality business rule type
All knobits of Data quality.
Source: DAMA-DMBOK: Data Management Body of Knowledge, 2nd edition (revised), chapter 13: Data Quality, element QV-9