Recognises a ratio over mismatched populations
The numerator counts items the denominator excludes, or the reverse.
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 | 81% | Not shown |
| gemini-3.5-flash-lite | Low cost | 35% | Not shown |
| gpt-6-luna | Low cost | 34% | Not shown |
| claude-haiku-5-5 | Low cost | 36% | 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: Both over the same population in scope
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: KP-002 NPL: numerator all loans 90+ dpd, denominator performing retail loans only Acceptable: Both over the same loans in scope
Also known as: Numerator and denominator from different populations
Related knobits
Builds on
All 19 knobits of Define metrics and KPIs.
Source: Review checklist 02-metric-definitions, row 1 (11179; DMBOK)