Question Answering on Trivia QA Hard
37.83F1 ScoreRAG
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| RAGModel=Llama3-8b-instruct2025.02 | 37.83 | — | |
| LLM-DiscrimModel=Llama3-8b-instruct2025.02 | 37.6 | — | |
| ENDModel=Llama3-8b-instruct2025.02 | 37.34 | 96 | |
| LLM-DiscrimModel=Mistral-v0.3-instruct2025.02 | 37.32 | — | |
| ENDModel=Mistral-v0.3-instruct2025.02 | 37.23 | 95 | |
| ENDModel=Qwen2.5-7b-instruct2025.02 | 36.93 | 92 | |
| LLM-DiscrimModel=Qwen2.5-7b-instruct2025.02 | 36.4 | — | |
| RAGModel=Qwen2.5-7b-instruct2025.02 | 35.71 | — | |
| RAGModel=Mistral-v0.3-instruct2025.02 | 35.63 | — |