| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Regression | synthetic datasets #2 (test) | MSE0 | 64 | |
| Regression | synthetic datasets #1 1.0 (test) | MSE0 | 64 | |
| Rotation Averaging | Synthetic Datasets | Rotational Error (R)0 | 60 | |
| Confidence interval construction | synthetic datasets #1 | 95% CI Coverage Rate1 | 48 | |
| Reciprocal Recommendation | Synthetic datasets n=75, m=50, e=log 10 independent trials | Expected Matches136.4 | 36 | |
| Tabular Data Clustering | Synthetic datasets | ARI Rank13 | 13 | |
| Single Image Reflection Separation | Synthetic Datasets Average (540) (test) | PSNR26.4 | 12 | |
| Conditional Average Treatment Effect (CATE) estimation | 10 Synthetic Datasets | PEHE0.515 | 9 | |
| Causal Discovery | Synthetic datasets | Adjacency Recall84.3 | 6 | |
| Missing Value Imputation | Synthetic datasets (test) | RMSE0.1196 | 6 | |
| Regression | 10 Synthetic Datasets High-dimensional Nonlinear Regression Simulation (10 datasets average) | FSR0 | 6 | |
| Novel View Synthesis | Synthetic datasets (test) | Rendering Speed (x)1 | 5 | |
| Novel View Synthesis | Synthetic Datasets LDR-NE (test) | PSNR37.53 | 5 | |
| Novel View Synthesis | Synthetic Datasets LDR-OE (test) | PSNR41.1 | 5 | |
| SAT solving | Synthetic datasets Larger Distribution | Success Rate9.13 | 5 | |
| SAT solving | Synthetic datasets Same Distribution | SR63.16 | 5 | |
| Clustering | 30,000 Synthetic Datasets 5D Hard (test) | Mean AMI Rank1.56 | 3 | |
| Clustering | 30,000 Synthetic Datasets 2D Hard (test) | Mean AMI Rank1.6 | 3 | |
| Clustering | 30,000 Synthetic Datasets 5D Easy (test) | Mean AMI Rank1.57 | 3 | |
| Clustering | 30,000 Synthetic Datasets 2D Easy (test) | Mean AMI Rank1.57 | 3 | |
| Clustering | Synthetic datasets 5D Hard 30,000 sampled datasets (test) | Mean Purity Rank2.64 | 3 | |
| Clustering | Synthetic datasets 2D Hard 30,000 sampled datasets (test) | Mean Purity Rank2.58 | 3 | |
| Clustering | Synthetic datasets 5D Easy 30,000 sampled datasets (test) | Mean Purity Rank2.31 | 3 | |
| Clustering | Synthetic datasets 2D Easy 30,000 sampled (test) | Mean Purity Rank2.36 | 3 | |
| Model Selection | 5 Synthetic Datasets (unseen) | Performance0.9991 | 1 |