| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| VenusBench Mobile | Task-State Representation (Kimi-k2.5) | Success Rate (SR)26.27 | 4 | 24d ago | |
| MemGUI Memory | Task-State Representation (Kimi-k2.5) | Success Rate (SR)40.87 | 4 | 24d ago | |
| MemGUI-Bench | Task-State Representation (Kimi-k2.5) | Success Rate42.97 | 4 | 24d ago | |
| MobileWorld | Task-State Representation (Kimi-k2.5) | Success Rate (SR)58 | 4 | 24d ago |