CAIN-42 MCPGateCAIN PolicyForge: figures & benchmarks
Evidence for CAIN PolicyForge: 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.
2/2
claims matched when recorded
1
attack cases refused or flagged as claimed
41 ms
median round trip (min 37, max 41), incl. network
| # | Kind | Claim | Recorded value | HTTP | ms |
|---|---|---|---|---|---|
| C01 | control | Observed: read reports -> Within the baseline. | true | 200 | 41 |
| C02 | attack | Observed: delete prod-db -> Would widen permission: flagged. | false | 200 | 37 |
Copy the table (paste into a spreadsheet)
id kind claim recorded_value expected http ms recorded_at C01 control Observed: read reports -> Within the baseline. true [true] 200 41 2026-11-03T22:54:36+00:00 C02 attack Observed: delete prod-db -> Would widen permission: flagged. false [false] 200 37 2026-11-03T22:54:37+00:00
Download: figures.tsv · transcript.json (full answers) · whole kit
How to read these numbers
- Recorded 2026-11-03T22:54:37+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.