Commonsense Reasoning on CommonsenseQA (Acc, Tokens, Ratio)
57AccuracyMCTS + EquivPruner
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| MCTS + EquivPrunerModel=Qwen2.5-Math-7B-Instruct, Search Strategy=MCTS + EquivPruner2025.05 | 57 | 35,129 | 88.2 | |
| Vanilla MCTSModel=Qwen2.5-Math-7B-Instruct, Search Strategy=Vanilla MCTS2025.05 | 56 | 39,827 | 100 |