Question Answering on SimpleQA (F1 score)
45.27F1 ScoreGPT-4o (2024-11-20)
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o (2024-11-20)Version=2024-11-202025.08 | 45.27 | |
| Llama + LoRRBackbone=Llama3.2-3B, Optimization=LoRR2025.08 | 21.47 | |
| Llama + DPOBackbone=Llama3.2-3B, Optimization=DPO2025.08 | 20.96 | |
| Qwen (Base)Backbone=Qwen2.5-3B, Mode=Base2025.08 | 18.64 | |
| Qwen + LoRRBackbone=Qwen2.5-3B, Optimization=LoRR2025.08 | 18.59 | |
| Qwen + DPOBackbone=Qwen2.5-3B, Optimization=DPO2025.08 | 18.31 | |
| Llama (Base)Backbone=Llama3.2-3B, Mode=Base2025.08 | 17.11 |