List your company

Web Navigation Question Answering on WebWalker QA (Pass@1)

72.2Pass@1Tongyi DeepResearch
60.7663.7366.769.67Oct 28, 2025

Evaluation results

MethodLinks
Tongyi DeepResearchAgent Type=DeepResearch Agent, Configuration=30B-A3B2025.1072.2
OpenAI o3Agent Type=LLM-based ReAct Agent2025.1071.7
GLM 4.5Agent Type=LLM-based ReAct Agent2025.1065.6
Kimi K2Agent Type=LLM-based ReAct Agent2025.1063
Claude-4-SonnetAgent Type=LLM-based ReAct Agent2025.1061.7
DeepSeek-V3.1Agent Type=LLM-based ReAct Agent2025.1061.2