Audited evaluation suite
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Annotation-enabled Rollout Collection | Audited Evaluation Suite | Data Success Rate90.5 | 14 | |
| Action Annotation Quality | Audited Evaluation Suite | Pass Rate60.3 | 13 | |
| Visual Annotation Quality Assessment | Audited evaluation suite | Part Accuracy91.5 | 4 | |
| Visual-Language Bundle Quality Assessment | Audited evaluation suite | Semantic Score93.1 | 4 |
Showing 4 of 4 rows