| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Logical Reasoning | KK | Test Accuracy47.5 | 28 | |
| Logical Reasoning | KK All | Accuracy53.6 | 21 | |
| Logical Reasoning | KK 6–8 ppl. | Accuracy27.5 | 21 | |
| Logical Reasoning | KK 4–5 ppl. | Accuracy60.3 | 21 | |
| Logical Reasoning | KK 2–3 ppl. | Accuracy86.8 | 21 | |
| Logical Reasoning | KK hard | Accuracy73.5 | 8 | |
| Logical Reasoning | KK easy | Accuracy90 | 8 | |
| Machine Reading Comprehension | Kk Kazakh | ROUGE-L6.9 | 4 | |
| Puzzle Solving | KK | Pass@1 Accuracy50.14 | 2 |