| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Out-of-Domain Generalization | Out-of-Domain Generalization Suite Aggregate | Average Accuracy78.18 | 38 | |
| General Reasoning | Out-of-Domain Generalization Suite BGQA, CRUX, STGQA, TableBench, MMLU STEM | BGQA Accuracy60.4 | 21 |