| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| BrowseComp-plus | Accuracy78.41 | 22 | 7d ago | ||
| WebWalkerQA | MemEvolve + Flash-Searcher | Success Rate81.18 | 18 | 3mo ago | |
| WebWalkerQA Full Set | MANGO | Overall Success Rate52.5 | 15 | 1mo ago | |
| WebWalkerQA Multi-source | MANGO | Success Rate (Easy)43.75 | 15 | 1mo ago | |
| WebWalkerQA Single-source | MANGO | Success Rate (Easy)63.75 | 15 | 1mo ago | |
| WebQA (200 held-out questions) | MAGE | Accuracy62.7 | 7 | 21d ago |