Mathematical Reasoning on ACP
36.71AccuracyQwen2.5-3B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen2.5-3BEvaluation Protocol=Single, Backbone Model=Qwen2.5-3B2025.10 | 36.71 | |
| Falcon3-7BEvaluation Protocol=Single, Backbone Model=Falcon3-7B2025.10 | 36.29 | |
| K-LVR (1-Bytes)Evaluation Protocol=Ensemble (PoE), Vocabulary Strategy=1-Bytes2025.10 | 35.43 | |
| K-LVR (MCV)Evaluation Protocol=Ensemble (PoE), Vocabulary Strategy=MCV2025.10 | 34.71 | |
| UnionEvaluation Protocol=Ensemble (PoE), Vocabulary Strategy=Union2025.10 | 25.86 | |
| Naive (MCV)Evaluation Protocol=Ensemble (PoE), Vocabulary Strategy=Naive (MCV)2025.10 | 25.71 |