| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Oolong | SLIDERS | Accuracy68 | 10 | 1mo ago | |
| Loong | SLIDERS | Accuracy78.57 | 10 | 1mo ago | |
| FinanceBench (FB) | SLIDERS | Accuracy89.33 | 10 | 1mo ago | |
| LongBench | Qwen-LiteCoST | NarQA Score30.4 | 6 | 2mo ago | |
| FinQ100 | SLIDERS | Accuracy60.18 | 4 | 1mo ago |