CAIN-42 CAIN StudioEvidence library · family
Performance
11 tested rules in the 'performance' family, 11 held.
Last reviewed 2026-10-01
11 of 11 held niche Benchmarks, coverage & performance
What this family tests
Every rule the CAIN-42 test suites recorded under the family performance, across 1 evidence bundle. Each rule links to its own page with the recorded result and an in-browser check of the file it came from.
| ID | Rule | Bundle | Result |
|---|---|---|---|
| E36-PERF-task_success | performance dimension task_success is evidence | E36 | held |
| E36-PERF-latency | performance dimension latency is evidence | E36 | held |
| E36-PERF-cost | performance dimension cost is evidence | E36 | held |
| E36-PERF-reliability | performance dimension reliability is evidence | E36 | held |
| E36-PERF-governance_compliance | performance dimension governance_compliance is evidence | E36 | held |
| E36-PERF-proof_completeness | performance dimension proof_completeness is evidence | E36 | held |
| E36-PERF-recovery_quality | performance dimension recovery_quality is evidence | E36 | held |
| E36-PERF-incident_rate | performance dimension incident_rate is evidence | E36 | held |
| E36-PERF-false_actions | performance dimension false_actions is evidence | E36 | held |
| E36-PERF-false_refusals | performance dimension false_refusals is evidence | E36 | held |
| E36-PERF-resource_efficiency | performance dimension resource_efficiency is evidence | E36 | held |
Other families in this niche
bench_family · bench_category · coverage · property · telemetry · fabric_component · radar · swe · harness · regression · corpus · end_to_end · completion · latency · f2t · false_completion · failure_to_test
Try CAIN-42 on your own agents
Create a free account and every new account starts with a 7-day trial of the full platform. Or try the sandbox first, with no account at all.
Create a free account → · Try the sandbox · See the whole ecosystem