Web Browsing and Navigation (Chinese) on BrowseComp-ZH
65Avg@3OpenAI-GPT-5-high
Evaluation Results
| Method | Links | |
|---|---|---|
| OpenAI-GPT-5-highType=Foundation Models with Tools2025.11 | 65 | |
| OpenAI-o3Type=Foundation Models with Tools2025.11 | 58.1 | |
| MiroThinker-v1.0-72BParameters=72B2025.11 | 55.6 | |
| GLM-4.6Type=Foundation Models with Tools2025.11 | 49.5 | |
| DeepSeek-V3.1Type=Foundation Models with Tools2025.11 | 49.2 | |
| Minimax-M2Type=Foundation Models with Tools2025.11 | 48.5 | |
| DeepSeek-V3.2Type=Foundation Models with Tools2025.11 | 47.9 | |
| MiroThinker-v1.0-30BParameters=30B2025.11 | 47.8 | |
| Tongyi-DeepResearch-30BType=Research Agents2025.11 | 46.7 | |
| OpenAI DeepResearchType=Research Agents2025.11 | 42.9 | |
| Claude-4.5-SonnetType=Foundation Models with Tools2025.11 | 40.8 | |
| MiroThinker-v1.0-8BParameters=8B2025.11 | 40.2 | |
| DeepMiner-32B-RLType=Research Agents2025.11 | 40.1 | |
| WebExplorer-8B-RLType=Research Agents2025.11 | 32 | |
| Claude-4-SonnetType=Foundation Models with Tools2025.11 | 29.1 | |
| Kimi-K2-0905Type=Foundation Models with Tools2025.11 | 22.2 |