Explains deriving a scorecard headline from its critical lines
A headline is the worst critical line or the count of critical lines below threshold, never an average a failing critical element can hide in; the report states the limitations of the data (BCBS 239 Principle 7; DMBOK2 ch. 13, 2.7.5).
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 | 99% | Mastered |
| gemini-3.5-flash-lite | Low cost | 77% | Not shown |
| gpt-6-luna | Low cost | 99% | Mastered |
| claude-haiku-5-5 | Low cost | 99% | Mastered |
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: A headline is the worst critical line or the count of critical lines below threshold, never an average a failing critical element can hide in; the report states the limitations of the data (BCBS 239 Principle 7; DMBOK2 ch. 13, 2.7.5).
How it is assessed: Answers a written question on the scorecard headline correctly
Related knobits
Builds on
Needed for
All 10 knobits of Set data quality service levels and the scorecard.
Source: Practice the stage 7 reference and review checklist rest on