Question Answering on Natural QA Easy
70.69F1 ScoreLLM-Discrim
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| LLM-DiscrimModel=Llama3-8b-instruct2025.02 | 70.69 | — | |
| RAGModel=Qwen2.5-7b-instruct2025.02 | 70.18 | — | |
| ENDModel=Llama3-8b-instruct2025.02 | 69.8 | 100 | |
| RAGModel=Llama3-8b-instruct2025.02 | 69.4 | — | |
| ENDModel=Qwen2.5-7b-instruct2025.02 | 67.8 | 96 | |
| RAGModel=Mistral-v0.3-instruct2025.02 | 61.76 | — | |
| LLM-DiscrimModel=Qwen2.5-7b-instruct2025.02 | 60.09 | — | |
| ENDModel=Mistral-v0.3-instruct2025.02 | 57.53 | 100 | |
| LLM-DiscrimModel=Mistral-v0.3-instruct2025.02 | 48.39 | — |