List your company

Difficulty on DBE-KT (test)

70.99AAChatEval
53.653258.154162.65567.1559Mar 7, 2025

Evaluation results

MethodLinks
ChatEvalScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0370.9959.88
QG-SMSScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0369.4464.2
SwapScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0368.3153.7
VanillaScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0367.2849.38
CoTScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0364.238.89
MetricsScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0364.248.77
ReferenceScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.0362.9645.06
BERTScoreScoring Protocol=Individual Scoring2025.0361.73—
QSalienceScoring Protocol=Individual Scoring2025.0360.49—
KDA_largeScoring Protocol=Individual Scoring2025.0354.32—