Web Navigation Question Answering on WebWalker QA (Pass@1)
72.2Pass@1Tongyi DeepResearch
Evaluation Results
| Method | Links | |
|---|---|---|
| Tongyi DeepResearchAgent Type=DeepResearch Agent, Configuration=30B-A3B2025.10 | 72.2 | |
| OpenAI o3Agent Type=LLM-based ReAct Agent2025.10 | 71.7 | |
| GLM 4.5Agent Type=LLM-based ReAct Agent2025.10 | 65.6 | |
| Kimi K2Agent Type=LLM-based ReAct Agent2025.10 | 63 | |
| Claude-4-SonnetAgent Type=LLM-based ReAct Agent2025.10 | 61.7 | |
| DeepSeek-V3.1Agent Type=LLM-based ReAct Agent2025.10 | 61.2 |