Explains reusable quality check and audit code modules
Shareable, linkable code that runs the same checks and audit controls (record counts, totals, rule results) wherever data are processed, and records the results as metadata.
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: Shareable, linkable code that runs the same checks and audit controls (record counts, totals, rule results) wherever data are processed, and records the results as metadata.
How it is assessed: Answers a CDMP-style multiple-choice question on the quality check and audit code module
All knobits of Data quality.
Source: DAMA-DMBOK: Data Management Body of Knowledge, 2nd edition (revised), chapter 13: Data Quality, element QV-26