| gaia | MiroThinker-v1.0-72B | Accuracy81.9 | | 59 | 1mo ago |
| Browse Comp-ZH | | Score81.3 | | 50 | 3mo ago |
| Deep Search Tasks (test) | SALE w/o memory | Pass@191.3 | | 42 | 4mo ago |
| Browse Comp | Kimi-K2.5 | Score74.9 | | 38 | 3mo ago |
| BrowseComp-ZH | | Accuracy66.6 | | 35 | 1mo ago |
| BrowseComp-ZH (test) | | Accuracy58.1 | | 27 | 4mo ago |
| BrowseComp (test) | | Accuracy49.7 | | 27 | 4mo ago |
| xbench DeepSearch (test) | Tongyi-DeepResearch | Accuracy75 | | 26 | 4mo ago |
| XBench DeepSearch | Web2BigTable | Accuracy73 | | 24 | 2mo ago |
| GAIA text-only (val) | Tongyi-DeepResearch | Accuracy70.9 | | 24 | 4mo ago |
| Browsecomp | | Accuracy52 | | 24 | 1mo ago |
| BrowseComp v1.0 (test) | | Success Rate55 | | 23 | 1mo ago |
| BrowseComp-ZH v1.0 (test) | | Success Rate59 | | 22 | 1mo ago |
| XBench-DS v1.0 (test) | | Success Rate68 | | 22 | 1mo ago |
| xBench DeepSearch DS-2505 | SMTL-30B-300 | Score82 | | 20 | 3mo ago |
| xbench-DS | Qwen3-30B-A3B-thinking-SFT + SAPO | Accuracy75 | | 16 | 1mo ago |
| hle | ECHO | Accuracy11.4 | | 16 | 24d ago |
| BrowseComp EN | | Score67.6 | | 15 | 3mo ago |
| xBench DeepSearch (05) | | Score75 | | 14 | 4mo ago |
| HLE text-only | | Score40.8 | | 14 | 4mo ago |
| GAIA text-only | | Score0.757 | | 14 | 4mo ago |
| X-Bench | | Score (%)75 | | 14 | 4mo ago |
| BrowseComp-Plus | | Score70 | | 13 | 4mo ago |
| xBench-DeepSearch DS-2510 | | Score75 | | 12 | 3mo ago |
| SEAL 0 | Nanbeige4.1-3B | Score41.44 | | 11 | 4mo ago |