Recognises unrecognised special category data
Free text or codes revealing health or other Art. 9 data, classified by their label.
Can AI do this?
AI does this well Most of the tested AI models master this. 3 of 4 models in the current benchmark master it.
| Model | Tier | Probability of mastery | Status |
|---|---|---|---|
| gemini-4-argon | Flagship | 98% | Mastered |
| gemini-3.5-flash-lite | Low cost | 8% | Not shown |
| gpt-6-luna | Low cost | 96% | Mastered |
| claude-haiku-5-5 | Low cost | 96% | Mastered |
Mastered means a probability of at least 90% that the model has this knobit, estimated from its graded answers. “Not shown” means the answers do not settle it either way. How the models are tested.
What it looks like in practice
Expected result: The column with the special category at restricted
How it is assessed: Flags the deficient case and passes the acceptable one. Deficient: CO-010 hardship_case.reason_text, confidential, personal only Acceptable: restricted, special category
Also known as: Special category data not recognised
Related knobits
Builds on
- S-254 Explains special categories of personal data
- S-1801 Distinguishes personal data from special categories of personal data
All 16 knobits of Classify data.
Source: Review checklist 02-classification, row 8 (GDPR Art. 9)