S3
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Clinical diagnosis | S3 1.0 (test) | Precision98 | 36 | |
| Cluster count selection | S3 | Selected Cluster Count10 | 21 | |
| Clustering | S3 N(200) | ACC88.1 | 20 | |
| Synthetic Function Optimization | S3 Perm. Rosen. | Median LogGap1.9114 | 14 | |
| Narrative report generation | S3 1.0 (test) | RQI Score39.8 | 12 | |
| Heterogeneous Treatment Effect Estimation | S3 zeta=3, no overlap Synthetic (test) | RMSE (L=10)0.225 | 9 | |
| Nuclear Segmentation | S3 | Coverage0.9944 | 6 | |
| Human Novel-view Rendering | S3 4K | PSNR30.0311 | 6 | |
| Human Novel-view Rendering | S3 1K | PSNR33.196 | 6 | |
| Point-level consensus correctness prediction | S3 | AUPRC93.2 | 4 | |
| Task performance and governance | S3 Threshold | CDL46.5 | 2 | |
| Clustering | S3 | SmM0.6703 | 1 |
Showing 12 of 12 rows