CAIN-42 CAIN StudioEU AI Act Classifier: figures & benchmarks
Evidence for EU AI Act Classifier: 1. Evidence pack · 2. Answers to buyer questions · 3. Figures & benchmarks · 4. Selling tools · IHVRK kit · Learn it · why these pages exist
Every number on this page is read from the signed transcript inside the IHVRK kit; none is typed in by hand.
6/6
claims matched when recorded
4
attack cases refused or flagged as claimed
97 ms
median round trip (min 76, max 120235), incl. network
| # | Kind | Claim | Recorded value | HTTP | ms |
|---|---|---|---|---|---|
| C01 | control | An email spam filter -> The Commission's own example of minimal-risk AI. | "minimal" | 200 | 91 |
| C02 | control | A customer-service chatbot -> People must be told they are talking to an AI. | "limited" | 200 | 97 |
| C03 | attack | Ranks job applicants and filters CVs -> Employment decisions are a named high-risk use. | "high" | 200 | 120235 |
| C04 | attack | Scores exams to decide university admission -> Education admission is a named high-risk use. | "high" | 200 | 20144 |
| C05 | attack | Predicts who will commit a crime from personality -> Predicting crime from profiling alone is banned. | "unacceptable" | 200 | 89 |
| C06 | attack | Live facial recognition in streets for police -> Real-time public biometric identification by police is banned except in narrow cases. | "unacceptable" | 200 | 76 |
Copy the table (paste into a spreadsheet)
id kind claim recorded_value expected http ms recorded_at C01 control An email spam filter -> The Commission's own example of minimal-risk AI. "minimal" ["minimal"] 200 91 2026-11-03T22:48:44+00:00 C02 control A customer-service chatbot -> People must be told they are talking to an AI. "limited" ["limited"] 200 97 2026-11-03T22:48:44+00:00 C03 attack Ranks job applicants and filters CVs -> Employment decisions are a named high-risk use. "high" ["high"] 200 120235 2026-11-03T22:50:45+00:00 C04 attack Scores exams to decide university admission -> Education admission is a named high-risk use. "high" ["high"] 200 20144 2026-11-03T22:51:06+00:00 C05 attack Predicts who will commit a crime from personality -> Predicting crime from profiling alone is banned. "unacceptable" ["unacceptable"] 200 89 2026-11-03T22:51:06+00:00 C06 attack Live facial recognition in streets for police -> Real-time public biometric identification by police is banned except in narrow cases. "unacceptable" ["unacceptable"] 200 76 2026-11-03T22:51:07+00:00
Download: figures.tsv · transcript.json (full answers) · whole kit
How to read these numbers
- Recorded 2026-11-03T22:51:07+00:00 against cainstudio.online from our build host; times include the internet round trip.
- They show these inputs, not every possible input. Known misses are on the limits page.
- This is not a load test, an SLA or a third-party benchmark. Re-run it yourself:
python3 verify.py --live.