Recognises a gap in a partition of cases
A set of rules divides a concept into cases and the cases do not cover it. The uncovered case silently has no rule.
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 | 83% | Not shown |
| gemini-3.1-pro-preview* | Flagship | 1% | Not shown |
| gpt-6-astra* | Flagship | 6% | Not shown |
| claude-fable-5-1* | Flagship | 82% | Not shown |
| gemini-3.8-flash* | Mid tier | 0% | Not shown |
| gpt-6.1-sol* | Mid tier | 6% | Not shown |
| claude-sonnet-5-5* | Mid tier | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 6% | Not shown |
| gpt-6-luna | Low cost | 34% | Not shown |
| claude-haiku-5-5 | Low cost | 32% | 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 case no rule covers
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: Rules for status OPN and CLS, while the value set also allows DOR and BLK Acceptable: A rule per value, or one rule over the whole value set, so adding a value forces a decision
Also known as: Gap in a partition (data rule)
Related knobits
Builds on
All 23 knobits of Document data rules in SBVR.
Source: Review checklist 02-data-rules (data-quality), row 9; formerly data-modelling K-309