Define business terms in the glossary
The outcome: defines business terms in a glossary, free of circularity, homonyms and hidden rules.
Builds on: Design the metamodel.
Which AI model is best at define business terms in the glossary?
Best result for define business terms in the glossary: gemini-4-argon (95% test score).
| Model | Provider | Tier | Test score | Knobits mastered (expected) | Cost per test run |
|---|---|---|---|---|---|
| gemini-4-argon | Flagship | 95% | 92% | $0.021 | |
| gemini-3.1-pro-preview* | Flagship | 67% | 81% | $0.20 | |
| gpt-6-astra* | OpenAI | Flagship | 92% | 94% | $0.45 |
| claude-fable-5-1* | Anthropic | Flagship | 92% | 99% | $0.85 |
| gemini-3.8-flash* | Mid tier | 85% | 94% | $0.045 | |
| gpt-6.1-sol* | OpenAI | Mid tier | 92% | 94% | $0.077 |
| claude-sonnet-5-5* | Anthropic | Mid tier | 82% | 98% | $0.23 |
| gemini-3.5-flash-lite | Low cost | 48% | 46% | $0.003 | |
| gpt-6-luna | OpenAI | Low cost | 80% | 60% | $0.002 |
| claude-haiku-5-5 | Anthropic | Low cost | 50% | 74% | $0.006 |
* 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.
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 18 knobits of this activity
5 that AI does well, 5 it does partly, and 8 where people still lead.