| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| RAVEN v1 (test) | DCNet | Average Accuracy93.6 | 22 | 4d ago | |
| ARC-AGI 1 | Accuracy (Pass@2)98 | 15 | 4d ago | ||
| Abstract Visual Reasoning WReN (10^2 samples) | Soft TPR | Accuracy27.3 | 15 | 4d ago | |
| ARC-AGI 2 | Accuracy (Pass@2)100 | 14 | 4d ago | ||
| I-RAVEN v1 (test) | algebraic machine reasoning | Avg Accuracy93.2 | 11 | 4d ago | |
| VCog-Bench | Ours (RL) | CVR Score42.4 | 9 | 4d ago | |
| CLEVR-RPM | LEFT | Accuracy100 | 6 | 4d ago | |
| Abstract Visual Reasoning WReN (10^5 samples) | COMET | Accuracy98.3 | 5 | 4d ago | |
| Abstract Visual Reasoning 10^4 samples WReN | GVAE+ | Classification Accuracy68.4 | 5 | 4d ago | |
| Abstract Visual Reasoning dataset WReN | Soft TPR | Accuracy31.2 | 5 | 4d ago | |
| Abstract Visual Reasoning 10^3 samples WReN | Soft TPR | Accuracy41.2 | 4 | 4d ago | |
| Abstract Visual Reasoning WReN | Soft TPR | Accuracy36 | 4 | 4d ago | |
| Raven | MMICL | Accuracy34 | 3 | 3d ago |
