| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| TAXI1500 | MACRO | HLFR75.7 | 56 | 2mo ago | |
| SIB200 | MACRO | HLFR88.9 | 56 | 2mo ago | |
| GSM8K, IFEval, MMLU Aggregate | RA-MoE | Average Score40.9 | 15 | 1mo ago | |
| ABB | SYNDATA | Accuracy7.12 | 8 | 2mo ago | |
| In-House Multilingual Datasets SEA Average 1.0 | en Score90.15 | 8 | 4mo ago |