| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Multi-entity Reasoning | MEBench Set3 (>100) | Comparison Accuracy94.6 | 5 | |
| Multi-entity Reasoning | MEBench Set2 (11-100) | Comparison Accuracy95.2 | 5 | |
| Multi-entity Reasoning | MEBench Set1 (0-10) | Comparison Accuracy96.8 | 5 | |
| Multi-entity Reasoning | MEBench All sets | Comparison Acc93.4 | 5 |