List your company

Topic Coverage on EduAgent (test)

98.85AAQG-SMS
53.079664.962376.84588.7277Mar 7, 2025

Evaluation results

MethodLinks
QG-SMSScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0398.8598.62
MetricsScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0397.797.7
ReferenceScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.039796.31
ChatEvalScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0396.7795.85
VanillaScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0396.5495.39
SwapScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0395.8595.85
CoTScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0395.3992.63
BERTScoreScoring Protocol=Individual Scoring2025.0379.26—
KDA_largeScoring Protocol=Individual Scoring2025.0357.6—
QSalienceScoring Protocol=Individual Scoring2025.0354.84—