List your company

Multi-Hop Question Answering on WikiQA

80ScoreMDER-DR
34.55246.35158.1569.949Mar 11, 2026

Evaluation results

MethodLinks
MDER-DREvaluator=Soft EM, Match=true2026.038049
MDER-DREvaluator=LLM-as-a-Judge, Match=true2026.037966
MDER-DREvaluator=Soft EM, Match=false2026.0369.930
MDER-DREvaluator=LLM-as-a-Judge, Match=false2026.0369.847
Vector-RAGEvaluator=Soft EM, Match=true2026.0353.8—
Vector-RAGEvaluator=Soft EM, Match=false2026.0353.8—
GraphRAGEvaluator=Soft EM, Match=false2026.0351.6—
LLM-onlyEvaluator=Soft EM, Match=true2026.0351—
GraphRAGEvaluator=Soft EM, Match=true2026.0351—
Vector-RAGEvaluator=LLM-as-a-Judge, Match=true2026.0347.7—
Vector-RAGEvaluator=LLM-as-a-Judge, Match=false2026.0347.6—
GraphRAGEvaluator=LLM-as-a-Judge, Match=false2026.0342.4—
GraphRAGEvaluator=LLM-as-a-Judge, Match=true2026.0342.2—
LLM-onlyEvaluator=LLM-as-a-Judge, Match=true2026.0341.2—
LLM-onlyEvaluator=Soft EM, Match=false2026.0340.8—
LLM-onlyEvaluator=LLM-as-a-Judge, Match=false2026.0336.3—