| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Abstract Causal Reasoning | ACRE Systematicity | Query Accuracy67.44 | 10 | |
| Abstract Causal Reasoning | ACRE Compositionality | Query Accuracy69.04 | 10 | |
| Abstract Causal Reasoning | ACRE (I.I.D.) | Query Accuracy66.29 | 10 | |
| Visual Reasoning | ACRE 1.0 (systematicity) | Accuracy93.9 | 8 | |
| Visual Reasoning | ACRE compositionality 1.0 | Accuracy93.27 | 8 | |
| Visual Reasoning | ACRE I.I.D. 1.0 | Accuracy92.98 | 7 | |
| Success Rate | ACRE | Success Rate93 | 4 | |
| Causal Induction | ACRE (Systematic) | Overall Score93.9 | 3 | |
| Causal Induction | ACRE Compositional | All91.76 | 3 |