Mathematical Reasoning on Overall GSM8K, MATH-500, AMC 2023, AIME 2024, AIME 2025
79.8AccuracyMERA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MERABackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 79.8 | 3,864 | |
| DASTBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 76.1 | 5,225 | |
| MERABackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 76 | 4,680 | |
| OriginalBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 76 | 7,316 | |
| FCS+Ref.Backbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 75.4 | 4,883 | |
| O1-PrunerBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 74.9 | 5,804 | |
| FCS+Ref.Backbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 73.4 | 5,665 | |
| DEERBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 73.3 | 4,821 | |
| O1-PrunerBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 73.2 | 6,323 | |
| DASTBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 72.7 | 5,799 | |
| LCPOBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 72.5 | 5,894 | |
| No WaitBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 72 | 5,353 | |
| OriginalBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 71.2 | 7,488 | |
| DEERBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 69.2 | 5,484 | |
| LCPOBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 66.4 | 5,632 | |
| No WaitBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 66.1 | 6,333 | |
| MERABackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 62.4 | 4,862 | |
| FCS+Ref.Backbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 60.2 | 6,050 | |
| OriginalBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 58.6 | 8,379 | |
| DASTBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 57.9 | 6,242 | |
| O1-PrunerBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 57.7 | 6,892 | |
| DEERBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 57.5 | 5,481 | |
| No WaitBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 56.3 | 6,408 | |
| LCPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 55.2 | 6,207 |