| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| WebWalkerQA | WebThinker-32B-RL | Success Rate (Easy)58.8 | 41 | 1mo ago | |
| WebWalker QA | SMTL-30B-300 | Accuracy76.5 | 23 | 3mo ago | |
| WebWalker QA | Tongyi-DeepResearch-30B | Avg@372.2 | 9 | 3mo ago | |
| WebWalker QA | Tongyi DeepResearch | Pass@172.2 | 6 | 2mo ago |