Eval Harness
Last run
2026-05-27T01:02:44
Model
coach-v2:latest
Cases
14/320
Status
complete
voice_fidelity_median
4.0
banned_phrase_total
0
register_match_rate
0.536
regret_low_rate
0.518
would_send_rate
0.554
Full report →
Run eval harness (coach-v2:latest)