List your company

Agentic Web Browsing on BrowseComp-ZH

75.9Pass@1Yunque DeepResearch
4.1422.7741.460.03Sep 16, 2025Oct 8, 2025Oct 30, 2025Nov 21, 2025Dec 13, 2025Jan 4, 2026Jan 27, 2026

Evaluation results

MethodLinks
Yunque DeepResearchFramework Category=Close-source Agent Frameworks, Model Family=Gemini2026.0175.9—
Gemini 3 ProFramework Category=General LLMs + ReAct + Basic Tools2026.0167.1—
GLM 4.7Framework Category=General LLMs + ReAct + Basic Tools2026.0166.6—
DeepSeek-V3.2Framework Category=General LLMs + ReAct + Basic Tools2026.0165—
DeepSeek-V3.2thinking mode=true2025.1265—
GPT-5 HighFramework Category=General LLMs + ReAct + Basic Tools2026.0163—
GPT-5 High2025.1263—
Kimi K2 ThinkingFramework Category=General LLMs + ReAct + Basic Tools2026.0162.3—
Kimi-K2thinking mode=true2025.1262.3—
OpenAI-o3Framework Category=General LLMs + ReAct + Basic Tools2026.0158.1—
OpenAI-o3Paradigm=ReAct, Summary Tool=-2025.0958.1—
OpenAI o3Agent Type=LLM-based ReAct Agent2025.1058.1—
Tongyi DeepResearchAgent Type=DeepResearch Agent, Mode=Heavy Mode2025.1058.1—
DeepSeek-v3.1Paradigm=ReAct, Summary Tool=-2025.0949.2—
DeepSeek-V3.1Agent Type=LLM-based ReAct Agent2025.1049.2—
MiniMax M22025.1248.5—
AgentFoldFramework Category=Open-source Agent Frameworks, Model Family=Qwen2026.0147.3—
MiroFlowFramework Category=Open-source Agent Frameworks, Model Family=GPT2026.0147.1—
Tongyi DeepResearchFramework Category=Open-source Agent Frameworks, Model Family=Qwen2026.0146.7—
Tongyi DeepResearchAgent Type=DeepResearch Agent, Configuration=30B-A3B2025.1046.7—
WebResearcher (w/o TTS)Framework Category=Open-source Agent Frameworks, Model Family=Qwen2026.0145.2—
OpenAI DeepResearchFramework Category=Close-source Agent Frameworks, Model Family=GPT2026.0142.9—
OpenAI DeepResearchAgent Type=DeepResearch Agent2025.1042.9—
Claude-4.5-SonnetFramework Category=General LLMs + ReAct + Basic Tools2026.0142.4—
Claude-4.5-Sonnet2025.1242.4—
GLM 4.5Agent Type=LLM-based ReAct Agent2025.1037.5—
Claude-4Paradigm=ReAct, Summary Tool=-2025.0929.1—
Claude-4-SonnetAgent Type=LLM-based ReAct Agent2025.1029.1—
Kimi-K2Paradigm=ReAct, Summary Tool=-2025.0928.8—
Kimi K2Agent Type=LLM-based ReAct Agent2025.1028.8—
WebSailor-30BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.0927.346.4
WebSailor-30BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.0927.141.5
WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-235B2025.0925.742.2
WebSailor-30BParadigm=MEM1, Summary Tool=-2025.092541.2
WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-30B2025.0924.840.1
WebSailor-30BParadigm=Recent History, Summary Tool=-2025.0924.140.1
WebSailor-30BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.0924.142.6
WebSailor-30BParadigm=ReAct, Summary Tool=-2025.0923.938.4
WebSailor-7BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.0919.235.6
WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-235B2025.0918.132.9
WebSailor-7BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.0917.230.8
WebSailor-7BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.0917.132.2
WebSailor-3BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.0915.228
WebSailor-7BParadigm=Recent History, Summary Tool=-2025.0915.228
WebSailor-3BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.0913.724.6
WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-30B2025.0913.326.6
WebSailor-3BParadigm=Recent History, Summary Tool=-2025.0913.224.3
WebSailor-7BParadigm=ReAct, Summary Tool=-2025.0913.225.6
WebSailor-3BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.091323.5
WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-235B2025.0911.123.9
WebSailor-3BParadigm=ReAct, Summary Tool=-2025.098.217
WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-30B2025.096.914.5