Dashboard
Eval dashboard
Check readiness, start targeted eval runs, and jump into case coverage without scanning raw run tables.
Preset run
Start a saved preset
Use this path for smoke, regression, critical, or scenario packs that already have their cases and variants saved.
No presets are available for this suite.
Readiness has not loaded yet. Launch will check blockers before creating the run.
Eval readiness
Checking model defaults, databases, and coverage...
Latest run summary
Run #7
PX Chat / Golden Master • Aug 31, 09:13 AM
Status
done_with_warnings
Pass rate
73%
Graded
252
Avg final
4.54
Gate
fail
Suites
Case coverage
PX Chat
Golden Master
Suite slug: pxchat
Cases
279
Latest status
done_with_warnings
Pass rate
73%
Graded
252
Latest run #7 • Aug 31, 09:13 AM
Advanced diagnostics
IDK rate
0.0%
Empty retrieval
0.0%
Format violations
0.0%
Language violations
0.0%