Mathematical Reasoning on MATH 500 (Acc, Len, L-Acc)
82.6AccuracyEffi. Reasoning
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Effi. ReasoningBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 82.6 | 2,395 | 69.5 | |
| Bingo-ABase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 82.2 | 894 | 77.6 | |
| Vanilla PPOBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 81.4 | 2,771 | 66.2 | |
| DASTBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 81.2 | 1,770 | 71.9 | |
| Bingo-EBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 80.6 | 779 | 76.7 | |
| kimi-k1.5Base Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 80.4 | 1,692 | 71.6 | |
| DemystifyingBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 80.2 | 1,411 | 73 | |
| O1-PrunerBase Model=DeepSeek-R1-Distill-Qwen-1.5B2025.06 | 74.4 | 991 | 69.8 |