Explains additivity of facts
Additive, semi-additive (balances, not across time) and non-additive (ratios, recomputed from parts) facts (Kimball and Ross 2013).
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 | 91% | Not shown |
| gemini-3.5-flash-lite | Low cost | 81% | Not shown |
| gpt-6-luna | Low cost | 89% | Not shown |
| claude-haiku-5-5 | Low cost | 83% | 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: Additive, semi-additive (balances, not across time) and non-additive (ratios, recomputed from parts) facts (Kimball and Ross 2013).
How it is assessed: Answers a written question on the fact additivity correctly
Related knobits
Builds on
Needed for
- W-203 Recognises a semi-additive balance summed over time
- W-205 Recognises a ratio averaged across segments
- W-231 Reconciles two values of one KPI into quantified effects
- W-232 Recomputes a ratio from summed numerators and denominators
All 19 knobits of Define metrics and KPIs.
Source: Practice the stage 2 reference and review checklist rest on