Explains partitions of a concept into cases
Cases that together cover a concept, without gaps or overlaps.
Can AI do this?
AI does this well Most of the tested AI models master this. 3 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 98% | Mastered |
| gemini-3.1-pro-preview* | Flagship | 50% | Not shown |
| gpt-6-astra* | Flagship | 52% | Not shown |
| claude-fable-5-1* | Flagship | 91% | Not shown |
| gemini-3.8-flash* | Mid tier | 51% | Not shown |
| gpt-6.1-sol* | Mid tier | 53% | Not shown |
| claude-sonnet-5-5* | Mid tier | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 16% | Not shown |
| gpt-6-luna | Low cost | 92% | Mastered |
| claude-haiku-5-5 | Low cost | 93% | Mastered |
* 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: Cases that together cover a concept, without gaps or overlaps
How it is assessed: Finds the uncovered case in sample partitions
Related knobits
Needed for
All 23 knobits of Document data rules in SBVR.
Source: Data-management practice used by the stage 2 reference and review checklist; formerly data-modelling K-358