Single-Hop QA on NQ
48.5AccuracySLEA-RL
Evaluation Results
| Method | Links | |
|---|---|---|
| SLEA-RLBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 48.5 | |
| IGPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 46.7 | |
| GiGPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 46.4 | |
| SkillRLBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 45.9 | |
| ZeroSearchBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 43.6 | |
| EvolveRBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 43.5 | |
| GSPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 41.5 | |
| RLOOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 40.7 | |
| GRPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 40.3 | |
| Search-R1Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 39.3 | |
| PPOBase Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 38.7 | |
| Reinforce++Base Model=Qwen2.5-7B-Instruct, Method Category=RL Methods2026.03 | 34.3 | |
| RAGBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 27.4 | |
| R1-InstructBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 21 | |
| Search-o1Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 19.4 | |
| CoTBase Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 12.8 | |
| Qwen2.5Base Model=Qwen2.5-7B-Instruct, Method Category=Prompting2026.03 | 11.6 |