PhysBench
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Physical Reasoning | PhysBench | S1 Score97.1 | 13 | |
| Physical understanding | PhysBench official (test) | Avg Score63.4 | 12 | |
| Physical Perception | PhysBench | PhysBench Score64.4 | 9 | |
| Visual Question Answering | PhysBench | Accuracy58.3 | 6 |
Showing 4 of 4 rows