WalkXR-AI / eval / runs / EVAL-2026-04-21-MEM-TEST / summary / metrics_by_scenario.csv
metrics_by_scenario.csv
Raw
scenario_id,turns,mean_latency_ms,refusal_rate,persona_hit_rate,rag_hit_rate,memory_recall_rate,continuity_break_rate,errors
MEM-P01_MEM-M01,10,14371.0,0.0,0.6,1.0,0.0,0.0,0
MEM-P02_MEM-M01,10,12859.9,0.0,0.6,1.0,0.5,0.0,0