Question Answering on Humanity's Last Exam
51.7Pass@1Yunque DeepResearch
Evaluation results
| Method | Links | |
|---|---|---|
| Yunque DeepResearchFramework Category=Close-source Agent Frameworks, Model Family=Gemini2026.01 | 51.7 | |
| Gemini 3 ProFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 45.8 | |
| Kimi K2 ThinkingFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 44.9 | |
| GLM 4.7Framework Category=General LLMs + ReAct + Basic Tools2026.01 | 42.8 | |
| DeepSeek-V3.2Framework Category=General LLMs + ReAct + Basic Tools2026.01 | 40.8 | |
| GPT-5 HighFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 35.2 | |
| Tongyi DeepResearchFramework Category=Open-source Agent Frameworks, Model Family=Qwen2026.01 | 32.9 | |
| Claude-4.5-SonnetFramework Category=General LLMs + ReAct + Basic Tools2026.01 | 32 | |
| WebResearcher (w/o TTS)Framework Category=Open-source Agent Frameworks, Model Family=Qwen2026.01 | 28.8 | |
| MiroFlowFramework Category=Open-source Agent Frameworks, Model Family=GPT2026.01 | 27.2 | |
| Gemini DeepResearchFramework Category=Close-source Agent Frameworks, Model Family=Gemini2026.01 | 26.9 | |
| Kimi ResearcherFramework Category=Close-source Agent Frameworks, Model Family=Kimi2026.01 | 26.9 | |
| OpenAI DeepResearchFramework Category=Close-source Agent Frameworks, Model Family=GPT2026.01 | 26.6 | |
| OpenAI-o3Framework Category=General LLMs + ReAct + Basic Tools2026.01 | 20.2 | |
| DeepAgentFramework Category=Open-source Agent Frameworks, Model Family=QwQ2026.01 | 20.2 | |
| OAgentFramework Category=Open-source Agent Frameworks, Model Family=Claude2026.01 | 15.4 |