Question Answering on TriviaQA (pass@1)
82.8Pass@1Qwen2.5-32B-Instruct + SSP
Evaluation results
| Method | Links | |
|---|---|---|
| Qwen2.5-32B-Instruct + SSPTraining Paradigm=Scaling to Larger Models, SSP Integration=true2025.10 | 82.8 | |
| Qwen2.5-32B-InstructTraining Paradigm=Scaling to Larger Models, SSP Integration=false2025.10 | 78.4 | |
| Qwen3-8B + SSPTraining Paradigm=Generalization Across Model Families, SSP Integration=true2025.10 | 78.2 | |
| Search-R1-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 78 | |
| Qwen2.5-14B-Instruct + SSPTraining Paradigm=Scaling to Larger Models, SSP Integration=true2025.10 | 77.8 | |
| Qwen2.5-14B-InstructTraining Paradigm=Scaling to Larger Models, SSP Integration=false2025.10 | 77 | |
| Qwen3-8BTraining Paradigm=Generalization Across Model Families, SSP Integration=false2025.10 | 76 | |
| LLaMA-3.1-8B + SSPTraining Paradigm=Generalization Across Model Families, SSP Integration=true2025.10 | 75.8 | |
| Search-R1-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 75.4 | |
| R-Search-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 74.2 | |
| Qwen2.5-7B-Base + SSPTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=true2025.10 | 73.6 | |
| Qwen2.5-7B-Instruct + SSPTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=true2025.10 | 73.4 | |
| R-Search-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 71 | |
| ZeroSearch-7B + SSPTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=true2025.10 | 69 | |
| ZeroSearch-7BTraining Paradigm=Continual Training on Search-Specialized Agents, SSP Integration=false2025.10 | 66.6 | |
| LLaMA-3.1-8BTraining Paradigm=Generalization Across Model Families, SSP Integration=false2025.10 | 65.2 | |
| Qwen2.5-7B-InstructTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=false2025.10 | 64 | |
| Qwen2.5-7B-BaseTraining Paradigm=From-Scratch Training on Base and Instruct Models, SSP Integration=false2025.10 | 33.2 |