Recognises a control slower than the report it protects
The control runs less often than the report it protects, so most reports go out unchecked.
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 | 62% | Not shown |
| gemini-3.5-flash-lite | Low cost | 18% | Not shown |
| gpt-6-luna | Low cost | 49% | Not shown |
| claude-haiku-5-5 | Low cost | 63% | 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 control and the frequency needed
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: Monthly report; CT-004 reconciliation frequency: quarterly Acceptable: frequency: monthly, before distribution
Also known as: Control slower than the report
Related knobits
Builds on
All 21 knobits of Map BCBS 239 to controls.
Source: Review checklist 04-regulatory-mapping, row 12 (BCBS P3, P10)