FinePhyEval
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Correlation with Human Judgments | FinePhyEval | Pearson's r0.478 | 7 | |
| Correlation with Human Likert Scores | FinePhyEval | Pearson's r0.478 | 5 | |
| Video Generation Evaluation | FinePhyEval | Object Coherence Score0.98 | 4 |
Showing 3 of 3 rows