Explains data profiling measures
Null rates, distinct counts, ranges, value frequencies, key uniqueness and validity against documentation (DMBOK2 ch. 13; ISO/IEC 25024).
Can AI do this?
AI does this well Most of the tested AI models master this. 4 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 100% | Mastered |
| gpt-6-luna | Low cost | 100% | Mastered |
| claude-haiku-5-5 | Low cost | 100% | Mastered |
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: Null rates, distinct counts, ranges, value frequencies, key uniqueness and validity against documentation (DMBOK2 ch. 13; ISO/IEC 25024).
How it is assessed: Answers a written question on the data profiling correctly
Related knobits
Builds on
Needed for
- G-532 Raises a decision for its owner instead of taking it
- N-101 Recognises an undocumented code value in use
- N-103 Recognises a supposedly unique key with duplicates
- N-104 Recognises an undocumented null meaning
- N-105 Recognises an implausible date in a source
All 13 knobits of Analyse and profile the sources.
Source: Practice the stage 1 reference and review checklist rest on