WalkXR-AI / eval / runs / EVAL-2025-08-14-v0.1 / summary / metrics_by_scenario.csv
metrics_by_scenario.csv
Raw
scenario_id,turns,mean_latency_ms,refusal_rate,persona_hit_rate,rag_hit_rate,errors
SM-P01_SM-M01,5,3128.6,0.0,1.0,,0
SM-P01_SM-M02,5,6998.0,0.0,1.0,,0
SM-P01_SM-M03,5,2904.8,0.0,0.8,,0
SM-P01_SM-M04,5,2714.8,0.0,1.0,,0
SM-P01_SM-M05,5,2465.0,0.0,1.0,,0
SM-P01_SM-M06,5,2686.8,0.0,1.0,,0
SM-P01_SM-M07,5,4032.8,0.0,1.0,,0
SM-P01_SM-M08,5,2178.4,0.0,1.0,,0
SM-P02_SM-M01,5,2474.0,0.0,1.0,,0
SM-P02_SM-M02,5,4489.4,0.0,1.0,,0
SM-P02_SM-M03,5,2383.6,0.0,0.6,,0
SM-P02_SM-M04,5,3747.4,0.0,0.0,,0
SM-P02_SM-M05,5,5472.6,0.0,1.0,,0
SM-P02_SM-M06,5,2634.6,0.0,1.0,,0
SM-P02_SM-M07,5,3669.0,0.0,1.0,,0