Mathematical Reasoning on Math Word
24.6AccuracyLIDAS
Evaluation Results
| Method | Links | |
|---|---|---|
| LIDASModel Size=1.7B, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 24.6 | |
| MIDASModel Size=1.7B, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 24.01 | |
| BaselineModel Size=1.7B, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 23.28 | |
| LIDASModel Size=1.7B, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 18.59 | |
| LN-ScalingModel Size=1.7B, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 17.84 | |
| MIDASModel Size=1.7B, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 16.07 | |
| BaselineModel Size=1.7B, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 13.75 | |
| MIDASModel Size=360M, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 13.43 | |
| LIDASModel Size=360M, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 12.3 | |
| LN-ScalingModel Size=1.7B, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 11 | |
| LN-ScalingModel Size=360M, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 8.45 | |
| BaselineModel Size=360M, Cooldown Protocol=Math, Five-shot prompting=true2025.12 | 8.1 | |
| MIDASModel Size=360M, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 4.39 | |
| LIDASModel Size=360M, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 4.36 | |
| BaselineModel Size=360M, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 3.69 | |
| LN-ScalingModel Size=360M, Cooldown Protocol=Standard, Five-shot prompting=true2025.12 | 2.89 |