| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Visual Grounded Reasoning | TreeBench | Overall Score54.8 | 17 | |
| Perception | TWI-oriented TreeBench online setting | Accuracy70.5 | 16 | |
| Reasoning | TWI-oriented TreeBench online setting | Accuracy37.1 | 16 | |
| Perception | TWI-oriented TreeBench (offline) | Accuracy71.1 | 12 | |
| Reasoning | TreeBench TWI-oriented (offline) | Accuracy37.1 | 12 |