List your company

Difficulty on EduAgent (test)

68.95Accuracy (AA)ChatEval
50.916455.598260.2864.9618Mar 7, 2025

Evaluation results

MethodLinks
ChatEvalScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0368.9551.61
QG-SMSScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0368.5565.32
ReferenceScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0366.5351.61
SwapScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0366.5354.84
MetricsScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0365.3253.22
VanillaScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0363.7150.8
CoTScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0361.6932.26
KDA_largeScoring Protocol=Individual Scoring2025.0360.48—
QSalienceScoring Protocol=Individual Scoring2025.0354.03—
BERTScoreScoring Protocol=Individual Scoring2025.0351.61—