Question Answering on QA Benchmark Suite Aggregate
0.331Average ScoreSearch-R1++
Evaluation results
| Method | Links | |
|---|---|---|
| Search-R1++Base Model=Qwen2.5-3B, Method Category=RL trained Deep Research Agents2026.02 | 0.331 | |
| Search-R1Base Model=Qwen2.5-3B, Method Category=RL trained Deep Research Agents2026.02 | 0.289 | |
| R1-baseBase Model=Qwen2.5-3B, Method Category=RL Trained LLM without Retrieval2026.02 | 0.229 | |
| ReActBase Model=Qwen2.5-3B, Method Category=Training free Deep Research Agent2026.02 | 0.055 |