| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Reward Modeling | OGRBench | Ubuntu Accuracy88.1 | 24 | |
| Trajectory completion judgment | OGRBench (Overall) | Accuracy88.2 | 20 | |
| Trajectory completion judgment | OGRBench Web | Accuracy87.4 | 20 | |
| Trajectory completion judgment | OGRBench MacOS | Accuracy93.5 | 20 | |
| Trajectory completion judgment | OGRBench Windows | Accuracy85.5 | 20 | |
| Trajectory completion judgment | OGRBench Mobile | Accuracy91 | 20 | |
| Trajectory completion judgment | OGRBench Ubuntu | Accuracy88.7 | 20 |