Mathematical Reasoning on GSM8K (Acc. (%))
94.14Accuracy (%)GTD
Evaluation Results
| Method | Links | |
|---|---|---|
| GTDTime (s/inst.)=7.92025.10 | 94.14 | |
| MaASTime (s/inst.)=8.82025.10 | 92.3 | |
| G-DesignerTime (s/inst.)=9.22025.10 | 92.09 | |
| DyLANTime (s/inst.)=8.52025.10 | 89.98 | |
| LLM-DebateTime (s/inst.)=11.72025.10 | 89.47 | |
| Vanilla (CoT)Time (s/inst.)=1.82025.10 | 87.45 |