Leak rate
The share of tested prompts that reached the provider when they should have been blocked in that run context.
Verifiable evidence surface
Evidence surface
Paired benchmarks for enforcement behavior.
Published runs are used to inspect how a deterministic gate behaves under test. They are not a model leaderboard and they are not an intelligence ranking surface.
| Date (UTC) | Model | Pack | Prompts | Baseline leaks | Gated leaks | Blocked benign | Outcome | Evidence |
|---|---|---|---|---|---|---|---|---|
| Loading paired benchmark runs... | ||||||||
Reading the results
Core terms
Blocked benign
The count of prompts treated as harmless in the run summary but blocked by the gate.
Suite hash
A hash binding for the evaluated suite so the reviewed material can be tied back to a specific test input set.
Audit links
Run, audit, and artefact links let reviewers inspect the published evidence directly rather than relying on a summary claim.