Skilirium

Recognises mixed and-or without precedence in a rule

Q-217 · Skill knobit · Activity: Document data rules in SBVR · Competence: Data quality

Precedence is undefined, so two readings are both defensible.

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.

ModelTierProbability of masteryStatus
gemini-4-argonFlagship 75%Not shown
gemini-3.1-pro-preview*Flagship 99%Mastered
gpt-6-astra*Flagship 100%Mastered
claude-fable-5-1*Flagship 99%Mastered
gemini-3.8-flash*Mid tier 99%Mastered
gpt-6.1-sol*Mid tier 100%Mastered
claude-sonnet-5-5*Mid tier 99%Mastered
gemini-3.5-flash-liteLow cost 42%Not shown
gpt-6-lunaLow cost 74%Not shown
claude-haiku-5-5Low cost 76%Not shown

* 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 two readings and the parenthesised one intended

How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: "Each account must specify an IBAN and a branch or an account holder" Acceptable: Split into two rules, or parenthesise: "...an IBAN and (a branch or an account holder)" (RUL-021)

Also known as: "and" with "or" in one clause (data rule)

Related knobits

Builds on

All 23 knobits of Document data rules in SBVR.

Source: Review checklist 02-data-rules (data-quality), row 17; formerly data-modelling K-317