Recognises duplicate governance metrics
Two metrics measuring the same thing with different formulas or populations. They will disagree, and both will be quoted.
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 | 76% | Not shown |
| gemini-3.5-flash-lite | Low cost | 70% | Not shown |
| gpt-6-luna | Low cost | 77% | Not shown |
| claude-haiku-5-5 | Low cost | 78% | 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 pair and the survivor
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: GM-008 Arrears completeness and GM-013 Share of loans with an arrears day count Acceptable: One metric, one definition; the other retired
Also known as: Duplicate metrics
Related knobits
Builds on
All 21 knobits of Build the governance scorecard.
Source: Review checklist 06-scorecard, row 14 (DMBOK)