List your company

RAG-Completeness on ASQA (test)

0.54Kendall's TauJury-on-Demand
0.3320.3860.440.494Dec 1, 2025

Evaluation results

MethodLinks
Jury-on-DemandJury Strategy=Dynamic2025.120.54
Claude 3.7 SONNETJury Strategy=Single Judge2025.120.42
Static (Avg-All)Jury Strategy=Static, Aggregation=Average All2025.120.38
Static (Avg-TopK)Jury Strategy=Static, Aggregation=Average TopK2025.120.38
Static (W-Reg)Jury Strategy=Static, Aggregation=Weighted-Regression2025.120.36
Static (W-Tau)Jury Strategy=Static, Aggregation=Weighted-Tau2025.120.34