Design the metamodel
The outcome: models the metadata classes and relationships the sources can populate and the glossary can hold.
Builds on: State the metadata requirements and strategy.
Which AI model is best at design the metamodel?
| Model | Provider | Tier | Test score | Knobits mastered (expected) | Cost per test run |
|---|---|---|---|---|---|
| gemini-4-argon | Flagship | – | 90% | $0.021 | |
| gemini-3.5-flash-lite | Low cost | – | 14% | $0.003 | |
| gpt-6-luna | OpenAI | Low cost | – | 64% | $0.002 |
| claude-haiku-5-5 | Anthropic | Low cost | – | 75% | $0.006 |
Test score: mean rubric score on the test tasks for this activity. Knobits mastered: expected share of the activity's knobits the model masters. Cost: mean API cost of one test run at list prices, half price for answers sent as a batch. Method and caveats.
The 12 knobits of this activity
1 that AI does well, 2 it does partly, and 9 where people still lead.