IntPhys
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Physics violation detection | IntPhys 2 | Mean Accuracy96.4 | 17 | |
| Intuitive Physics | IntPhys (dev) | O1 Score59.2 | 9 |
Showing 2 of 2 rows
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Physics violation detection | IntPhys 2 | Mean Accuracy96.4 | 17 | |
| Intuitive Physics | IntPhys (dev) | O1 Score59.2 | 9 |