| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Overall | Solvable Accuracy97.4 | 7 | 4d ago | ||
| AIME 24-25 | Solvable Accuracy95 | 7 | 4d ago | ||
| Maze Hard | Deepseek-V3.2-R | Solvable Accuracy98 | 7 | 4d ago | |
| Maze Easy | Deepseek-V3.2-R | Accuracy (Solvable)100 | 7 | 4d ago | |
| Hitori | Accuracy (Solvable)98 | 7 | 4d ago | ||
| HamPath | Solvable Accuracy100 | 7 | 4d ago | ||
| HamCycle | Solvable Accuracy100 | 7 | 4d ago | ||
| Game24 | Deepseek-V3.2-R | Solvable Accuracy98 | 7 | 4d ago |