| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| IOI | GIM | CPR3.54 | 30 | 1d ago | |
| Mixing dataset | DCD-divisive-SVD | CMD0.011 | 28 | 22d ago | |
| Mixing dataset IOI | CMD0.008 | 28 | 22d ago | ||
| Mixing dataset All tasks | CMD0.007 | 28 | 22d ago | ||
| Sequence Completion 1.0 (test) | DCD-kmeans-PCA | CPR1.014 | 28 | 22d ago | |
| Indirect Object Identification (IOI) 1.0 (test) | DCD-kmeans-PCA | CPR1.068 | 28 | 22d ago | |
| Mixing dataset All tasks 1.0 (test) | DCD-divisive-SVD | CPR1.035 | 28 | 22d ago | |
| MCQA | GIM | CPR2.52 | 21 | 1d ago | |
| Mixing dataset Entity Binding | DCD-kmeans-PCA | CMD0.013 | 18 | 22d ago | |
| Entity-binding 1.0 (test) | K-representative | CPR1.112 | 18 | 22d ago | |
| ARC Easy | GIM | CPR2.36 | 12 | 1d ago | |
| Mixing dataset Arithmetic | CMD74.3 | 9 | 22d ago | ||
| Arithmetic 1.0 (test) | K-representative | CPR1.017 | 9 | 22d ago | |
| Mechanistic Interpretability Benchmark (MIB) | IFR | IOI83 | 9 | 3mo ago | |
| ARC Challenge | GIM | CPR1.65 | 6 | 1d ago | |
| Arithmetic | GIM | CPR1.09 | 6 | 1d ago | |
| General | GIM | CPR2.13 | 6 | 1d ago |