Reasoning on r-GSM, Seven Objects, and Date
91.87AccuracyHoT
Evaluation results
| Method | Links | |
|---|---|---|
| HoTBase Model=๐2025.03 | 91.87 | |
| CoTBase Model=๐2025.03 | 88.94 | |
| HoTBase Model=Mean2025.03 | 88.04 | |
| ToTBase Model=๐2025.03 | 87.39 | |
| CoTBase Model=Mean2025.03 | 85.18 | |
| ToTBase Model=Mean2025.03 | 84.69 | |
| LtMBase Model=๐2025.03 | 84.38 | |
| HoTBase Model=โก2025.03 | 84.21 | |
| ToTBase Model=โก2025.03 | 81.98 | |
| Self-RefineBase Model=๐2025.03 | 81.74 | |
| CoVEBase Model=๐2025.03 | 81.54 | |
| CoTBase Model=โก2025.03 | 81.41 | |
| LtMBase Model=Mean2025.03 | 80.16 | |
| CoVEBase Model=Mean2025.03 | 77.81 | |
| Self-RefineBase Model=Mean2025.03 | 76.03 | |
| LtMBase Model=โก2025.03 | 75.94 | |
| CoVEBase Model=โก2025.03 | 74.07 | |
| Self-RefineBase Model=โก2025.03 | 70.32 |