Agentic Web Browsing on BrowseComp-ZH
75.9Pass@1Yunque DeepResearch
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Yunque DeepResearchFramework Category=Close-source Agent Frameworks, Model Family=Gemini2026.01 | 75.9 | — | |
| Gemini 3 ProFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 67.1 | — | |
| GLM 4.7Framework Category=General LLMs + ReAct + Basic Tools2026.01 | 66.6 | — | |
| DeepSeek-V3.2Framework Category=General LLMs + ReAct + Basic Tools2026.01 | 65 | — | |
| DeepSeek-V3.2thinking mode=true2025.12 | 65 | — | |
| GPT-5 HighFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 63 | — | |
| GPT-5 High2025.12 | 63 | — | |
| Kimi K2 ThinkingFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 62.3 | — | |
| Kimi-K2thinking mode=true2025.12 | 62.3 | — | |
| OpenAI-o3Framework Category=General LLMs + ReAct + Basic Tools2026.01 | 58.1 | — | |
| OpenAI-o3Paradigm=ReAct, Summary Tool=-2025.09 | 58.1 | — | |
| OpenAI o3Agent Type=LLM-based ReAct Agent2025.10 | 58.1 | — | |
| Tongyi DeepResearchAgent Type=DeepResearch Agent, Mode=Heavy Mode2025.10 | 58.1 | — | |
| DeepSeek-v3.1Paradigm=ReAct, Summary Tool=-2025.09 | 49.2 | — | |
| DeepSeek-V3.1Agent Type=LLM-based ReAct Agent2025.10 | 49.2 | — | |
| MiniMax M22025.12 | 48.5 | — | |
| AgentFoldFramework Category=Open-source Agent Frameworks, Model Family=Qwen2026.01 | 47.3 | — | |
| MiroFlowFramework Category=Open-source Agent Frameworks, Model Family=GPT2026.01 | 47.1 | — | |
| Tongyi DeepResearchFramework Category=Open-source Agent Frameworks, Model Family=Qwen2026.01 | 46.7 | — | |
| Tongyi DeepResearchAgent Type=DeepResearch Agent, Configuration=30B-A3B2025.10 | 46.7 | — | |
| WebResearcher (w/o TTS)Framework Category=Open-source Agent Frameworks, Model Family=Qwen2026.01 | 45.2 | — | |
| OpenAI DeepResearchFramework Category=Close-source Agent Frameworks, Model Family=GPT2026.01 | 42.9 | — | |
| OpenAI DeepResearchAgent Type=DeepResearch Agent2025.10 | 42.9 | — | |
| Claude-4.5-SonnetFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 42.4 | — | |
| Claude-4.5-Sonnet2025.12 | 42.4 | — | |
| GLM 4.5Agent Type=LLM-based ReAct Agent2025.10 | 37.5 | — | |
| Claude-4Paradigm=ReAct, Summary Tool=-2025.09 | 29.1 | — | |
| Claude-4-SonnetAgent Type=LLM-based ReAct Agent2025.10 | 29.1 | — | |
| Kimi-K2Paradigm=ReAct, Summary Tool=-2025.09 | 28.8 | — | |
| Kimi K2Agent Type=LLM-based ReAct Agent2025.10 | 28.8 | — | |
| WebSailor-30BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.09 | 27.3 | 46.4 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.09 | 27.1 | 41.5 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-235B2025.09 | 25.7 | 42.2 | |
| WebSailor-30BParadigm=MEM1, Summary Tool=-2025.09 | 25 | 41.2 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=Qwen3-30B2025.09 | 24.8 | 40.1 | |
| WebSailor-30BParadigm=Recent History, Summary Tool=-2025.09 | 24.1 | 40.1 | |
| WebSailor-30BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.09 | 24.1 | 42.6 | |
| WebSailor-30BParadigm=ReAct, Summary Tool=-2025.09 | 23.9 | 38.4 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.09 | 19.2 | 35.6 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-235B2025.09 | 18.1 | 32.9 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.09 | 17.2 | 30.8 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.09 | 17.1 | 32.2 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=GPT-OSS-120B2025.09 | 15.2 | 28 | |
| WebSailor-7BParadigm=Recent History, Summary Tool=-2025.09 | 15.2 | 28 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=ReSumTool-30B2025.09 | 13.7 | 24.6 | |
| WebSailor-7BParadigm=ReSum, Summary Tool=Qwen3-30B2025.09 | 13.3 | 26.6 | |
| WebSailor-3BParadigm=Recent History, Summary Tool=-2025.09 | 13.2 | 24.3 | |
| WebSailor-7BParadigm=ReAct, Summary Tool=-2025.09 | 13.2 | 25.6 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=DeepSeek-R1-671B2025.09 | 13 | 23.5 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-235B2025.09 | 11.1 | 23.9 | |
| WebSailor-3BParadigm=ReAct, Summary Tool=-2025.09 | 8.2 | 17 | |
| WebSailor-3BParadigm=ReSum, Summary Tool=Qwen3-30B2025.09 | 6.9 | 14.5 |