Recognises a duplicate rate measured after merging
A rate that is low by construction.
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 | 52% | Not shown |
| gemini-3.5-flash-lite | Low cost | 49% | Not shown |
| gpt-6-luna | Low cost | 51% | Not shown |
| claude-haiku-5-5 | Low cost | 50% | 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 rate measured on the sources before matching
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: MM-001 duplicate rate 0.3%, measured on the golden records Acceptable: Measured on the sources before matching
Also known as: Duplicate rate measured after merging
Related knobits
Builds on
All 13 knobits of Run the stewardship workflow and measure MDM.
Source: Review checklist 05-stewardship-metrics, row 4 (8000-8; 25024)