Web Navigation Question Answering on WebWalker QA (avg@3)
72.2Avg@3Tongyi-DeepResearch-30B
Evaluation Results
| Method | Links | |
|---|---|---|
| Tongyi-DeepResearch-30BType=Research Agents2025.11 | 72.2 | |
| OpenAI-o3Type=Foundation Models with Tools2025.11 | 71.7 | |
| AFM-32B-RLType=Research Agents2025.11 | 63 | |
| WebExplorer-8B-RLType=Research Agents2025.11 | 62.7 | |
| MiroThinker-v1.0-72BParameters=72B2025.11 | 62.1 | |
| Claude-4-SonnetType=Foundation Models with Tools2025.11 | 61.7 | |
| DeepSeek-V3.1Type=Foundation Models with Tools2025.11 | 61.2 | |
| MiroThinker-v1.0-30BParameters=30B2025.11 | 61 | |
| MiroThinker-v1.0-8BParameters=8B2025.11 | 60.6 |