Recognises contradicting data rules
Two rules on one fact type cannot both hold. Almost always a missing condition: one rule applies to a subtype and nobody wrote that down.
Can AI do this?
People still lead Few or none of the tested AI models showed they master this. 1 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 90% | Not shown |
| gemini-3.1-pro-preview* | Flagship | 84% | Not shown |
| gpt-6-astra* | Flagship | 100% | Mastered |
| claude-fable-5-1* | Flagship | 100% | Mastered |
| gemini-3.8-flash* | Mid tier | 100% | Mastered |
| gpt-6.1-sol* | Mid tier | 100% | Mastered |
| claude-sonnet-5-5* | Mid tier | 100% | Mastered |
| gemini-3.5-flash-lite | Low cost | 10% | Not shown |
| gpt-6-luna | Low cost | 9% | Not mastered |
| claude-haiku-5-5 | Low cost | 90% | Mastered |
* From the earlier benchmark of 2026-10: 10 data-modelling test tasks, 3 runs per task, graded by claude-opus-5-5. These models have not taken the current 123 tasks yet; the two methods differ, so compare their figures with care. They are left out of the “most models” counts and the best-model picks.
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 rule pair and the missing condition
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: BR-1: each account has exactly one interest rate and BR-2: it is prohibited that an account has an interest rate Acceptable: BR-1: each savings account has exactly one interest rate; BR-2: it is prohibited that a current account has an interest rate — the condition is in the rule, not in somebody's memory (ANO-001)
Also known as: Contradiction (data rule)
Related knobits
Builds on
Usually followed by
All 23 knobits of Document data rules in SBVR.
Source: Review checklist 02-data-rules (data-quality), row 1; formerly data-modelling K-301