| Browse Comp-ZH | | Score81.3 | | 50 | 3d ago |
| gaia | MiroThinker-v1.0-72B | Accuracy81.9 | | 43 | 15d ago |
| Deep Search Tasks (test) | SALE w/o memory | Pass@191.3 | | 42 | 1mo ago |
| Browse Comp | Kimi-K2.5 | Score74.9 | | 38 | 18d ago |
| BrowseComp-ZH (test) | | Accuracy58.1 | | 27 | 1mo ago |
| BrowseComp (test) | | Accuracy49.7 | | 27 | 1mo ago |
| xbench DeepSearch (test) | Tongyi-DeepResearch | Accuracy75 | | 26 | 1mo ago |
| GAIA text-only (val) | Tongyi-DeepResearch | Accuracy70.9 | | 24 | 1mo ago |
| xBench DeepSearch DS-2505 | SMTL-30B-300 | Score82 | | 20 | 18d ago |
| BrowseComp-ZH | TaS | Accuracy63.7 | | 17 | 1mo ago |
| BrowseComp EN | | Score67.6 | | 15 | 3d ago |
| xBench DeepSearch (05) | | Score75 | | 14 | 1mo ago |
| HLE text-only | | Score40.8 | | 14 | 1mo ago |
| GAIA text-only | | Score0.757 | | 14 | 1mo ago |
| X-Bench | | Score (%)75 | | 14 | 1mo ago |
| BrowseComp-Plus | | Score70 | | 13 | 1mo ago |
| xBench-DeepSearch DS-2510 | | Score75 | | 12 | 18d ago |
| SEAL 0 | Nanbeige4.1-3B | Score41.44 | | 11 | 1mo ago |
| xBench DeepSearch-10 | Nanbeige4.1-3B | Score39 | | 8 | 1mo ago |
| Xbench DeepSearch | QuarkMedSearch | Score81 | | 7 | 3d ago |
| Average webw., hle, gaia | Qwen3-8B + TEPOdense | Accuracy9.87 | | 7 | 1mo ago |
| Browsecomp | SAGE | Accuracy2.6 | | 6 | 1mo ago |
| hle | Musique | Accuracy8 | | 6 | 1mo ago |
| xbench DeepSearch (leaderboard) | - | - | | 0 | 1mo ago |
| webw. | - | - | | 0 | 1mo ago |