Recognises a subject-area definition defining nothing
Restates the name, or lists nothing that distinguishes the area.
Can AI do this?
Not settled yet The benchmark tested this, but the models' answers do not settle yet whether they master it. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 55% | Not shown |
| gemini-3.5-flash-lite | Low cost | 28% | Not shown |
| gpt-6-luna | Low cost | 57% | Not shown |
| claude-haiku-5-5 | Low cost | 53% | 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: The definition and the characteristics it needs
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: SA-008 Product: "Products." Acceptable: "The bank's offerings - account, loan and card products - with their terms and pricing rules."
Also known as: Definition that does not define
Related knobits
Builds on
All 17 knobits of Build the enterprise data model of subject areas.
Source: Review checklist 02-enterprise-data-model, row 9 (704)