Movie
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Goal-oriented Dialogue | Movie | Success Rate89.52 | 44 | |
| Feature Attribution | Movie | Comprehensiveness83 | 33 | |
| Agentic decision making | Movie | Score0.9 | 21 | |
| Named Entity Recognition | Movie | F1 Score76.2 | 19 | |
| Federated Recommendation | Movie | Recall20.87 | 18 | |
| Header Prediction | Movie (test) | Accuracy99.98 | 16 | |
| Sentiment Classification | Movie | Accuracy0.9117 | 16 | |
| Sentiment Analysis | Movie | Accuracy85.9 | 13 | |
| Recommendation | Movie | HR@1026.05 | 13 | |
| Row Classification | Movie (test) | Macro F1 (XGBoost)62.9 | 11 | |
| Text-to-Video generation | Movie 17 frames, 512x512 (val) | UR50.8 | 11 | |
| Matrix Completion | Movie 10M | RMSE0.815 | 10 | |
| Dialogue Evaluation | Movie Eval | Spearman Correlation0.649 | 10 | |
| CTR prediction | Movie 20M (test) | AUC97.04 | 10 | |
| Density Estimation | Movie Randomly-perturbed (test) | Log-likelihood-58.53 | 9 | |
| Density Estimation | Movie Adversarially-perturbed Ta (test) | Log-Likelihood-58.59 | 9 | |
| Text-to-Video generation | Movie 17 frames, 256x256 (val) | UR39.1 | 9 | |
| Video Reconstruction | Movie (val) | PSNR40.31 | 9 | |
| Sequential Recommendation | Movie (test) | HR@1012.29 | 9 | |
| Sentiment Analysis | Movie English (test) | F1 Score0.7478 | 8 | |
| Density Estimation | Movie Original T (test) | Log-Likelihood-52.81 | 7 | |
| Value Imputation | Movie | Accuracy70.77 | 7 | |
| Header Prediction | Movie | Accuracy99.98 | 7 | |
| Copyright Content Detection | Movie | Accg43.2 | 7 | |
| Slot Filling | Movie (test) | F1 Score83.98 | 7 |
Showing 25 of 39 rows