| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| VLM-Action-Judge | I-Bench (test) | IF Score2.557 | 7 | |
| Key-Mouse-Following | I-Bench (test) | Accuracy (Full)20.62 | 7 | |
| Interactive World Modeling | I-Bench 1.0 (test) | SC87.1 | 7 | |
| Interactive Video Generation | I-Bench User Study (test) | Action Following4.05 | 6 |