OSExpert-Eval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-Horizon Composite Skills | OSExpert-Eval | Execution Time (GIMP)18 | 10 | |
| Computer-use | OSExpert-Eval | Success Rate (LibreOffice)50 | 5 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-Horizon Composite Skills | OSExpert-Eval | Execution Time (GIMP)18 | 10 | |
| Computer-use | OSExpert-Eval | Success Rate (LibreOffice)50 | 5 |