Mathematical Reasoning on HMMT 24 (Pass@1)
74.4Pass@1RSE
Evaluation Results
| Method | Links | |
|---|---|---|
| RSEBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Recycling Search Experience, Iteration=It32026.01 | 74.4 | |
| RSEBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Recycling Search Experience, Iteration=It22026.01 | 73.7 | |
| PaCoReBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=PaCoRe, Iteration=It32026.01 | 73.1 | |
| PaCoReBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=PaCoRe, Iteration=It22026.01 | 72.2 | |
| RSEBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Recycling Search Experience, Iteration=It12026.01 | 71.9 | |
| PaCoReBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=PaCoRe, Iteration=It12026.01 | 70.6 | |
| Self-RefBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Self-Refine, Iteration=It32026.01 | 65.6 | |
| Self-RefBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Self-Refine, Iteration=It22026.01 | 64.5 | |
| Self-RefBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Self-Refine, Iteration=It12026.01 | 62.7 | |
| MV@128Backbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Majority Voting, Iteration=It02026.01 | 60.9 | |
| BaseBackbone=Qwen3-30B-A3B-Thinking-2507, Inference Strategy=Standard Sampling, Iteration=It02026.01 | 57.4 | |
| PaCoReBackbone=Qwen3-4B-Thinking-2507, Inference Strategy=PaCoRe, Iteration=It12026.01 | 56.7 | |
| RSEBackbone=Phi-4-Reasoning, Inference Strategy=Recycling Search Experience, Iteration=It32026.01 | 56.5 | |
| RSEBackbone=Qwen3-4B-Thinking-2507, Inference Strategy=Recycling Search Experience, Iteration=It32026.01 | 56 | |
| Self-RefBackbone=Qwen3-4B-Thinking-2507, Inference Strategy=Self-Refine, Iteration=It32026.01 | 49.7 | |
| MV@128Backbone=Qwen3-4B-Thinking-2507, Inference Strategy=Majority Voting, Iteration=It02026.01 | 43.3 | |
| BaseBackbone=Qwen3-4B-Thinking-2507, Inference Strategy=Standard Sampling, Iteration=It02026.01 | 42.6 | |
| BaseBackbone=Phi-4-Reasoning, Inference Strategy=Standard Sampling, Iteration=It02026.01 | 40.3 |