Question Answering on NQ (pass@1)
62.6pass@1Qwen2.5-32B-Instruct + SSP
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-32B-Instruct + SSPTraining Paradigm=Scaling to Larger Models, SSP Integration=true2025.10 | 62.6 | |
| LLaMA-3.1-8B + SSPTraining Paradigm=Generalization Across Model Families, SSP Integration=true2025.10 | 58 | |
| Qwen2.5-32B-InstructTraining Paradigm=Scaling to Larger Models, SSP Integration=false2025.10 | 58 | |
| Search-R1-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 57.8 | |
| Qwen2.5-14B-Instruct + SSPTraining Paradigm=Scaling to Larger Models, SSP Integration=true2025.10 | 57.4 | |
| Search-R1-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 56.6 | |
| Qwen3-8B + SSPTraining Paradigm=Generalization Across Model Families, SSP Integration=true2025.10 | 56 | |
| Qwen2.5-14B-InstructTraining Paradigm=Scaling to Larger Models, SSP Integration=false2025.10 | 56 | |
| Qwen2.5-7B-Instruct + SSPTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=true2025.10 | 54.8 | |
| Qwen2.5-7B-Base + SSPTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=true2025.10 | 54.2 | |
| ZeroSearch-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 54.2 | |
| Qwen3-8BTraining Paradigm=Generalization Across Model Families, SSP Integration=false2025.10 | 53.6 | |
| R-Search-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 52.4 | |
| ZeroSearch-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 52.2 | |
| R-Search-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 50.8 | |
| LLaMA-3.1-8BTraining Paradigm=Generalization Across Model Families, SSP Integration=false2025.10 | 50.2 | |
| Qwen2.5-7B-InstructTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=false2025.10 | 44.2 | |
| Qwen2.5-7B-BaseTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=false2025.10 | 32 |