| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| AR-Bench-DC | BALAR | Exact Accuracy61 | 23 | 2mo ago | |
| ARBench | DC Score46.7 | 16 | 2mo ago | ||
| ARBench-GN | TeamTR (Homogeneous) | Accuracy45.3 | 13 | 2mo ago | |
| ARBench SP | Accuracy43.1 | 13 | 2mo ago | ||
| AR-Bench-SP | BALAR | Non-strict Semantic Equivalence54 | 10 | 2mo ago |