Recognises a manual adjustment outside any control
Adjustments outside any control.
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 | 67% | Not shown |
| gemini-3.5-flash-lite | Low cost | 67% | Not shown |
| gpt-6-luna | Low cost | 67% | Not shown |
| claude-haiku-5-5 | Low cost | 66% | 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 recorded adjustment
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: MA "as usual", not in any control Acceptable: Recorded with amount, reason, approver; in the control totals
Also known as: Manual adjustment with no record
Related knobits
Builds on
Usually followed by
All 14 knobits of Populate the warehouse and reconcile it.
Source: Review checklist 04-population-reconciliation, row 7 (BCBS 239 P3)