| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Grammar Synthesis | L2 a^n b^n c^m | Accuracy100 | 11 | |
| Two-Sample Testing | L2 d=512 | Testing Power0.255 | 8 | |
| Two-Sample Testing | L2 d=256 | Testing Power33.8 | 8 | |
| ScaleUp | L2 ScaleUp | LPR99 | 5 | |
| Minimal Problem Solving | L2 3-view triang. (relaxed) | Template Size (R x C)217,248 | 4 | |
| Pattern Perception | L2 (out-of-distribution) | Accuracy (Local)75.6 | 2 |