Product
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text Classification | Product (test) | F1 Score78.3 | 22 | |
| Header Prediction | Product (test) | Accuracy99.97 | 16 | |
| Fraud | Product | ASR100 | 15 | |
| Row Classification | Product (test) | Macro-F1 (XGBoost)94.4 | 11 | |
| Image Retrieval | Product-M | AR@179.36 | 10 | |
| Personalized Image Generation | Product | Consistency0.3296 | 9 | |
| Sequential Recommendation | Product (test) | Recall@10.0055 | 8 | |
| Link Prediction | Product (test) | P@177.86 | 8 | |
| Value Imputation | Product | Accuracy79.77 | 7 | |
| Header Prediction | Product | Accuracy99.95 | 7 | |
| Personalized Video Generation | Product | Consistency0.6355 | 6 | |
| Collaborative identifier prediction | Product | Recall@101.26 | 5 | |
| Part-based Image Generation | Product | FID47.9 | 5 | |
| Clustering | Product | F1 Score59 | 2 | |
| Classification | Product | Validation Accuracy96.83 | 2 | |
| Human-LLM Agreement | Product Total All languages 1.0 (val) | Accuracy95.2 | 1 | |
| Human-LLM Agreement | Product French subset 1.0 (val) | Accuracy94 | 1 | |
| Human-LLM Agreement | Product Spanish subset 1.0 (val) | Accuracy94.7 | 1 | |
| Human-LLM Agreement | Product German 1.0 (val) | Accuracy95.3 | 1 | |
| Human-LLM Agreement | Product Italian 1.0 (val) | Accuracy96.4 | 1 |
Showing 20 of 20 rows