Recognises a set rule written as a row rule
A rule that can only be judged across rows — uniqueness, no overlap, a total, a reference to another table — written as a single-row predicate. It is not a weak check; it checks nothing.
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 | 37% | Not shown |
| gemini-3.1-pro-preview* | Flagship | 100% | Mastered |
| gpt-6-astra* | Flagship | 99% | Mastered |
| claude-fable-5-1* | Flagship | 100% | Mastered |
| gemini-3.8-flash* | Mid tier | 99% | Mastered |
| gpt-6.1-sol* | Mid tier | 99% | Mastered |
| claude-sonnet-5-5* | Mid tier | 99% | Mastered |
| gemini-3.5-flash-lite | Low cost | 36% | Not shown |
| gpt-6-luna | Low cost | 83% | Not shown |
| claude-haiku-5-5 | Low cost | 82% | Not shown |
* From the earlier benchmark of 2026-10: 10 data-modelling test tasks, 3 runs per task, graded by claude-opus-5-5. These models have not taken the current 123 tasks yet; the two methods differ, so compare their figures with care. They are left out of the “most models” counts and the best-model picks.
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: The rule and the set check it needs
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: DQ-004: account_identifier is unique, scope: row, expression: account_identifier IS NOT NULL Acceptable: scope: set and a query returning the duplicated IBANs (DQR-025)
Also known as: Set rule written as a row rule (data quality rule)
Related knobits
Builds on
All 30 knobits of Derive data quality rules.
Source: Review checklist 03-dq-rules (data-quality), row 16; Olson 2003; formerly data-modelling K-716