gpt-6.1-sol
gpt-6.1-sol masters 144 of the 199 benchmarked knobits of Data modelling: an expected 88% of the competence.
Data modelling, activity by activity
| Activity | Test score | Knobits mastered (expected) |
|---|---|---|
| Capture data requirements | 72% | 73% |
| Define business terms | 92% | 94% |
| Document data rules as SBVR fact types and rule statements | 88% | 94% |
| Build the conceptual model and taxonomies | 88% | 88% |
| Derive the logical data model | 89% | 89% |
| Design the physical data model | 86% | 92% |
| Derive data quality rules | 94% | 98% |
| Generate and review DDL | 70% | 78% |
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-405 Recognises a node without warrant 0%
- K-610 Recognises a surrogate key without natural-key uniqueness 0%
- K-203 Recognises a negative definition 0%
- K-309 Recognises a gap in a partition of cases 6%
- K-133 Recognises a missing or wrong requirement trace 10%
- K-828 Recognises a business date stored with a time of day 18%
- K-117 Recognises a missing or wrong requirement type 19%
- K-821 Recognises a restricted column without access design 21%
- K-810 Recognises a truncated identifier taken as the real name 21%
- K-519 Recognises undeclared subtype constraints 33%
- K-101 Recognises a data requirement making several claims 36%
- K-122 Recognises paraphrased data requirements 36%
- K-114 Recognises content filed under the wrong requirement 37%
- K-817 Recognises a length taken from sample data 38%