BrowseComp-ZH
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Deep Search | BrowseComp-ZH (test) | Accuracy58.1 | 27 | |
| Long-horizon agentic tasks | BrowseComp-ZH Our Settings | Pass@171.3 | 25 | |
| Web Research | BrowseComp-ZH | Pass@129.1 | 19 | |
| Search | BrowseComp-ZH (test) | Accuracy68.7 | 17 | |
| Web Browsing and Navigation (Chinese) | BrowseComp-ZH | Avg@365 | 16 | |
| Agentic Web Interaction | BrowseComp-ZH (test) | Pass@161.3 | 10 | |
| Long-horizon agentic tasks | BrowseComp-ZH Full | Pass@165 | 2 |
Showing 7 of 7 rows