Uses only identifiers the sources hold
Rules on fields each source actually carries, none invented
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 0 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 10% | Not mastered |
| gemini-3.5-flash-lite | Low cost | 8% | Not shown |
| gpt-6-luna | Low cost | 89% | Not shown |
| claude-haiku-5-5 | Low cost | 8% | Not 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: Rules on fields each source actually carries, none invented
How it is assessed: No rule depends on a field a source lacks
Related knobits
Builds on
All 16 knobits of Define the matching rules.
Source: Graded on its own by rmd-matching