Deep Research on XBench-DeepSearch original (test)
71Pass@1DeepSeek-V3.1
Evaluation Results
| Method | Links | |
|---|---|---|
| DeepSeek-V3.1Backbone Group=Large Size Foundation Models (> 100B)2026.01 | 71 | |
| DeepSeek-V3.2Backbone Group=Large Size Foundation Models (> 100B)2026.01 | 71 | |
| OpenAI-o3Backbone Group=Large Size Foundation Models (> 100B)2026.01 | 66.7 | |
| Claude-4-SonnetBackbone Group=Large Size Foundation Models (> 100B)2026.01 | 64.6 | |
| WebSailor-72BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 55 | |
| WebSailor-32BBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 53.3 | |
| WebExplorer-8B (RL)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=RL2026.01 | 53 | |
| Kimi-K2Backbone Group=Large Size Foundation Models (> 100B)2026.01 | 50 | |
| OffSeeker-8B (DPO)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=DPO2026.01 | 49 | |
| OffSeeker-8B (SFT)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=SFT2026.01 | 48 | |
| ASearcher-Web-QwQBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 42.1 | |
| WebDancer-QwQBackbone Group=Medium Size Deep Research Agents (30B-72B)2026.01 | 39 | |
| DeepDive-9B (RL)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=RL2026.01 | 38 | |
| DeepDive-9B (SFT)Backbone Group=Small Size Deep Research Agents (< 10B), Training Protocol=SFT2026.01 | 35 | |
| WebSailor-7BBackbone Group=Small Size Deep Research Agents (< 10B)2026.01 | 34.3 |