Web Browsing and Navigation on BrowseComp
68.9Avg@3 ScoreChatGPT-Agent
Evaluation Results
| Method | Links | |
|---|---|---|
| ChatGPT-AgentType=Research Agents2025.11 | 68.9 | |
| OpenAI-GPT-5-highType=Foundation Models with Tools2025.11 | 54.9 | |
| OpenAI DeepResearchType=Research Agents2025.11 | 51.5 | |
| OpenAI-o3Type=Foundation Models with Tools2025.11 | 49.7 | |
| MiroThinker-v1.0-72BParameters=72B2025.11 | 47.1 | |
| GLM-4.6Type=Foundation Models with Tools2025.11 | 45.1 | |
| Minimax-M2Type=Foundation Models with Tools2025.11 | 44 | |
| Tongyi-DeepResearch-30BType=Research Agents2025.11 | 43.4 | |
| MiroThinker-v1.0-30BParameters=30B2025.11 | 41.2 | |
| DeepSeek-V3.2Type=Foundation Models with Tools2025.11 | 40.1 | |
| DeepMiner-32B-RLType=Research Agents2025.11 | 33.5 | |
| MiroThinker-v1.0-8BParameters=8B2025.11 | 31.1 | |
| DeepSeek-V3.1Type=Foundation Models with Tools2025.11 | 30 | |
| Claude-4.5-SonnetType=Foundation Models with Tools2025.11 | 19.6 | |
| WebExplorer-8B-RLType=Research Agents2025.11 | 15.7 | |
| Claude-4-SonnetType=Foundation Models with Tools2025.11 | 12.2 | |
| AFM-32B-RLType=Research Agents2025.11 | 11.1 | |
| Kimi-K2-0905Type=Foundation Models with Tools2025.11 | 7.4 |