claude-sonnet-5-5
claude-sonnet-5-5 masters 145 of the 199 benchmarked knobits of Data modelling: an expected 91% of the competence.
Data modelling, activity by activity
| Activity | Test score | Knobits mastered (expected) |
|---|---|---|
| Capture data requirements | 79% | 75% |
| Define business terms | 82% | 98% |
| Document data rules as SBVR fact types and rule statements | 95% | 100% |
| Build the conceptual model and taxonomies | 96% | 94% |
| Derive the logical data model | 88% | 95% |
| Design the physical data model | 94% | 94% |
| Derive data quality rules | 90% | 92% |
| Generate and review DDL | 74% | 76% |
Where it falls short
The knobits with the lowest probability of mastery: review its output here most carefully.
- K-103 Recognises a statement outside the scope of data requirements 0%
- K-606 Recognises rolled-up subtypes losing conditional constraints 0%
- K-420 Recognises a structural error in a taxonomy hierarchy 0%
- K-816 Recognises one decimal scale for every currency 0%
- K-810 Recognises a truncated identifier taken as the real name 19%
- K-821 Recognises a restricted column without access design 21%
- K-117 Recognises a missing or wrong requirement type 22%
- K-723 Recognises a check failure with no capable owner 26%
- K-724 Recognises a check scheduled at the wrong moment 26%
- K-822 Recognises greenfield DDL aimed at a populated database 27%
- K-823 Recognises a drop script used as a rollback 27%
- K-101 Recognises a data requirement making several claims 34%
- K-114 Recognises content filed under the wrong requirement 36%
- K-121 Recognises duplicate data requirements 36%
- K-122 Recognises paraphrased data requirements 37%