Discrimination on DBE-KT (test)
66.66AAQG-SMS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| QG-SMSScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 66.66 | 56.99 | |
| ChatEvalScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 65.05 | 53.76 | |
| VanillaScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 63.98 | 49.46 | |
| CoTScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 62.9 | 34.41 | |
| SwapScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 62.9 | 48.39 | |
| MetricsScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 61.29 | 45.16 | |
| ReferenceScoring Protocol=Pairwise LLM-based, Base Model=GPT-4o2025.03 | 60.75 | 44.09 | |
| KDA_largeScoring Protocol=Individual Scoring2025.03 | 58.06 | — | |
| QSalienceScoring Protocol=Individual Scoring2025.03 | 47.31 | — | |
| BERTScoreScoring Protocol=Individual Scoring2025.03 | 30.11 | — |