Question Answering on SimpleQA (test)
4.05SimpleQA ScoreSFT-DPO + General Data
Evaluation results
| Method | Links | |
|---|---|---|
| SFT-DPO + General DataBase Model=Llama3.1-8B-Instruct, Alignment=SFT-DPO, Strategy=General Data2026.02 | 4.05 | |
| SFT + OGPSABase Model=Qwen2.5-7B-Instruct, Alignment=SFT, Strategy=OGPSA2026.02 | 3.61 | |
| SFT + General DataBase Model=Llama3.1-8B-Instruct, Alignment=SFT, Strategy=General Data2026.02 | 3.54 |