gemini-3.1-pro-preview
gemini-3.1-pro-preview masters 109 of the 199 benchmarked knobits of Data modelling: an expected 80% of the competence.
Data modelling, activity by activity
| Activity | Test score | Knobits mastered (expected) |
|---|---|---|
| Capture data requirements | 54% | 52% |
| Define business terms | 67% | 81% |
| Document data rules as SBVR fact types and rule statements | 74% | 86% |
| Build the conceptual model and taxonomies | 95% | 100% |
| Derive the logical data model | 79% | 94% |
| Design the physical data model | 81% | 84% |
| Derive data quality rules | 71% | 86% |
| Generate and review DDL | 64% | 61% |
Where it falls short
The knobits with the lowest probability of mastery: review its output here most carefully.
- K-626 Recognises a fact table of mixed grain 0%
- K-119 Recognises a guess recorded as fact 0%
- K-211 Recognises a definition carrying non-defining content 0%
- K-606 Recognises rolled-up subtypes losing conditional constraints 0%
- K-103 Recognises a statement outside the scope of data requirements 0%
- K-824 Recognises an environment baked into the script 0%
- K-816 Recognises one decimal scale for every currency 0%
- K-309 Recognises a gap in a partition of cases 1%
- K-306 Recognises circular derivation rules 5%
- K-133 Recognises a missing or wrong requirement trace 9%
- K-113 Recognises a business rule left inside another statement 10%
- K-828 Recognises a business date stored with a time of day 14%
- K-209 Recognises a hidden definition of a second concept 15%
- K-810 Recognises a truncated identifier taken as the real name 19%
- K-718 Recognises a misfiled data quality dimension 20%