Mathematical Reasoning on AIME 2025 (Accuracy, Tokens)
59.2AccuracyMERA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MERABackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 59.2 | 7,320 | |
| OriginalBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 56.4 | 12,752 | |
| DASTBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 56.2 | 10,298 | |
| FCS+Ref.Backbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 53.7 | 8,309 | |
| MERABackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 53.6 | 8,732 | |
| O1-PrunerBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 53.1 | 9,356 | |
| LCPOBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 50.2 | 10,405 | |
| FCS+Ref.Backbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 49.8 | 9,844 | |
| DASTBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 49.5 | 9,721 | |
| O1-PrunerBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 49.4 | 10,973 | |
| OriginalBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 48.2 | 13,276 | |
| DEERBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 47.3 | 9,723 | |
| No WaitBackbone=DeepSeek-R1-Distill-Qwen-14B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 45.3 | 8,280 | |
| LCPOBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 40.6 | 9,904 | |
| DEERBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 39.6 | 9,302 | |
| No WaitBackbone=DeepSeek-R1-Distill-Qwen-7B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 35.2 | 11,827 | |
| MERABackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 30.9 | 9,357 | |
| FCS+Ref.Backbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 28.6 | 11,624 | |
| OriginalBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 26.9 | 14,680 | |
| LCPOBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 24.7 | 10,075 | |
| O1-PrunerBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 24.1 | 12,701 | |
| DASTBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 20.6 | 10,647 | |
| No WaitBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 20.3 | 11,601 | |
| DEERBackbone=DeepSeek-R1-Distill-Qwen-1.5B, Zero-shot Chain-of-Thought (CoT)=true2025.08 | 20.2 | 9,890 |