Recognises a retention basis not covering the class
A cited provision that does not cover the class.
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 | 56% | Not shown |
| gemini-3.5-flash-lite | Low cost | 54% | Not shown |
| gpt-6-luna | Low cost | 48% | Not shown |
| claude-haiku-5-5 | Low cost | 56% | 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 citation and the provisions that do apply
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: RR-002 loan agreements cite MiFID II Art. 16(7) Acceptable: Contract and limitation law; AML for the relationship
Also known as: Legal basis that does not apply
Related knobits
Builds on
All 17 knobits of Set the retention and disposition schedule.
Source: Review checklist 02-retention-schedule, row 4 (DMBOK)