Human Evaluation Study
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Human Evaluation Study
3.664Average Rating Score
8
Human Evaluation Study
4.31Omission Score
7
Human Evaluation Study
84Human Preference (%)
6
Human Evaluation Study
4.5Satisfaction Score
4
Human Evaluation Study Generated 3D Scenes
2.506Overall Score
4
Human Evaluation Study
81Human Preference
4
Human Evaluation Study Counter-Speech Post-Edited
3.458FACT
3
Human Evaluation Study Aggregated across video generation categories
69Validity Rate
3
Human Evaluation Study (Good Players)
3.9Contributed Success
2