Recognises an unmeasured false-merge rate
Nothing measures false merges.
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 | 96% | Mastered |
| gemini-3.5-flash-lite | Low cost | 11% | Not shown |
| gpt-6-luna | Low cost | 96% | Mastered |
| claude-haiku-5-5 | Low cost | 96% | 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: The measurement and its sample
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: false_merge_rate: null Acceptable: Labelled sample, measured before go-live and quarterly
Also known as: No measured false-merge rate
Related knobits
Builds on
All 16 knobits of Define the matching rules.
Source: Review checklist 03-matching, row 6 (DMBOK)