List your company

Web Browsing and Task Completion on BrowseComp

58.3Pass@1 RateTongyi DeepResearch
10.35622.80335.2547.697Oct 28, 2025

Evaluation results

MethodLinks
Tongyi DeepResearchAgent Type=DeepResearch Agent, Mode=Heavy Mode2025.1058.3
OpenAI DeepResearchAgent Type=DeepResearch Agent2025.1051.5
OpenAI o3Agent Type=LLM-based ReAct Agent2025.1049.7
Tongyi DeepResearchAgent Type=DeepResearch Agent, Configuration=30B-A3B2025.1043.4
DeepSeek-V3.1Agent Type=LLM-based ReAct Agent2025.1030
OpenAI o4-miniAgent Type=LLM-based ReAct Agent2025.1028.3
GLM 4.5Agent Type=LLM-based ReAct Agent2025.1026.4
Kimi K2Agent Type=LLM-based ReAct Agent2025.1014.1
Claude-4-SonnetAgent Type=LLM-based ReAct Agent2025.1012.2