Deep Research on WebWalkerQA original (test)
72.2Pass@1Tongyi-DeepResearch
Evaluation results
| Method | Links | |
|---|---|---|
| Tongyi-DeepResearchBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 72.2 | |
| OpenAI-o3Backbone Group=Large Size Foundation Models (> 100B)2026.01 | 71.7 | |
| Kimi-K2Backbone Group=Large Size Foundation Models (> 100B)2026.01 | 63 | |
| Claude-4-SonnetBackbone Group=Large Size Foundation Models (> 100B)2026.01 | 61.7 | |
| OffSeeker-8B (DPO)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=DPO2026.01 | 61.7 | |
| DeepSeek-V3.1Backbone Group=Large Size Foundation Models (> 100B)2026.01 | 61.2 | |
| OffSeeker-8B (SFT)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=SFT2026.01 | 60 | |
| WebExplorer-8B (RL)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=RL2026.01 | 58 | |
| WebShaper-72BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 52.2 | |
| WebShaper-32BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 51.4 | |
| MiroThinker-32B-DPO-v0.1Backbone Group=Medium Size Deep Research Agents (30B-72B), Training Protocol=DPO2026.01 | 49.3 | |
| WebDancer-QwQBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 47.9 | |
| MiroThinker-8B-DPO-v0.1Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=DPO2026.01 | 45.7 | |
| ASearcher-Web-QwQBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 34.3 |