LIVE · 100 answersLast run: 38h agoJudge: gpt-4o-mini
Run eval

Per-Role Breakdown

Pass rates and metric means split by role template, sorted weakest first. Click a row to see which sessions contribute.

Role templateNPassCorrectnessCompletenessContextContextOpeningVoiceFaithfulness
unknown1000%0.500.410.480.440.410.400.45