| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Streaming Video Understanding | StreamingBench | Overall93.55 | 158 | |
| Real-time Visual Understanding | StreamingBench | Overall Score91.46 | 96 | |
| Real-Time Visual Understanding | StreamingBench Real-Time Visual Understanding (test) | OP89.5 | 33 | |
| Online Video Question Answering | StreamingBench | Overall Performance (OP)84.47 | 20 | |
| Streaming Video Reasoning | StreamingBench Real-Time | Object Perception (OP)89.47 | 14 | |
| Online Video Understanding | StreamingBench Real-Time | Real-Time Score77.3 | 13 | |
| Reactive Question Answering | StreamingBench excluding PO 1.0 (test) | Overall Performance (OP)76.96 | 9 | |
| Streaming video understanding | StreamingBench proactive | Accuracy82.8 | 8 | |
| Proactive Response | StreamingBench | Accuracy38 | 7 | |
| Online Video Understanding | StreamingBench | Real-time VU Score77.3 | 6 |