Math Reasoning on HLE Math-100 (Pass@1)
35.84Pass@1TMAS
Evaluation Results
| Method | Links | |
|---|---|---|
| TMASBackbone=Qwen3-30B-Thinking-2507, Iteration=It172026.05 | 35.84 | |
| TMASBackbone=Qwen3-30B-Thinking-2507, Iteration=It192026.05 | 35.38 | |
| TMASBackbone=Qwen3-30B-Thinking-2507, Iteration=It112026.05 | 33.72 | |
| TMASBackbone=Qwen3-30B-Thinking-2507, Iteration=It92026.05 | 33.22 | |
| PaCoReBackbone=Qwen3-30B-Thinking-2507, Iteration=It112026.05 | 33.16 | |
| TMASBackbone=Qwen3-30B-Thinking-2507, Iteration=It32026.05 | 33.03 | |
| PaCoReBackbone=Qwen3-30B-Thinking-2507, Iteration=It192026.05 | 32.78 | |
| PaCoReBackbone=Qwen3-30B-Thinking-2507, Iteration=It172026.05 | 32.75 | |
| PaCoReBackbone=Qwen3-30B-Thinking-2507, Iteration=It92026.05 | 32.69 | |
| PaCoReBackbone=Qwen3-30B-Thinking-2507, Iteration=It32026.05 | 32 | |
| RSEBackbone=Qwen3-30B-Thinking-2507, Iteration=It192026.05 | 31.75 | |
| RSEBackbone=Qwen3-30B-Thinking-2507, Iteration=It172026.05 | 31.13 | |
| V-RBackbone=Qwen3-30B-Thinking-2507, Iteration=It192026.05 | 30.41 | |
| MV@64Backbone=Qwen3-30B-Thinking-2507, Iteration=It12026.05 | 30.3 | |
| RSEBackbone=Qwen3-30B-Thinking-2507, Iteration=It112026.05 | 29.97 | |
| V-RBackbone=Qwen3-30B-Thinking-2507, Iteration=It172026.05 | 29.88 | |
| V-RBackbone=Qwen3-30B-Thinking-2507, Iteration=It112026.05 | 29.28 | |
| V-RBackbone=Qwen3-30B-Thinking-2507, Iteration=It92026.05 | 29.19 | |
| TMAS w/ Hybrid-RLBackbone=Qwen3-4B-Thinking-2507, Iteration=It192026.05 | 28.16 | |
| TMAS w/ Hybrid-RLBackbone=Qwen3-4B-Thinking-2507, Iteration=It172026.05 | 27.75 | |
| RSEBackbone=Qwen3-30B-Thinking-2507, Iteration=It92026.05 | 27.47 | |
| PaCoReBackbone=Qwen3-30B-Thinking-2507, Iteration=It12026.05 | 27.41 | |
| Self-RefineBackbone=Qwen3-30B-Thinking-2507, Iteration=It192026.05 | 27.12 | |
| TMAS w/ Hybrid-RLBackbone=Qwen3-4B-Thinking-2507, Iteration=It112026.05 | 26.34 | |
| Self-RefineBackbone=Qwen3-30B-Thinking-2507, Iteration=It112026.05 | 26.19 | |
| Self-RefineBackbone=Qwen3-30B-Thinking-2507, Iteration=It172026.05 | 26 | |
| Self-RefineBackbone=Qwen3-30B-Thinking-2507, Iteration=It92026.05 | 25.19 | |
| TMAS w/ Hybrid-RLBackbone=Qwen3-4B-Thinking-2507, Iteration=It32026.05 | 25.19 | |
| TMASBackbone=Qwen3-30B-Thinking-2507, Iteration=It12026.05 | 25.09 | |
| TMAS w/ Hybrid-RLBackbone=Qwen3-4B-Thinking-2507, Iteration=It92026.05 | 25.09 | |
| TMAS w/ Hybrid-RLBackbone=Qwen3-4B-Thinking-2507, Iteration=It12026.05 | 24.16 | |
| Self-RefineBackbone=Qwen3-30B-Thinking-2507, Iteration=It32026.05 | 23.78 | |
| RSEBackbone=Qwen3-30B-Thinking-2507, Iteration=It32026.05 | 23.31 | |
| V-RBackbone=Qwen3-30B-Thinking-2507, Iteration=It32026.05 | 21.91 | |
| RSEBackbone=Qwen3-30B-Thinking-2507, Iteration=It12026.05 | 21.28 | |
| Self-RefineBackbone=Qwen3-30B-Thinking-2507, Iteration=It12026.05 | 20.25 | |
| V-RBackbone=Qwen3-30B-Thinking-2507, Iteration=It12026.05 | 18.81 | |
| TMASBackbone=Qwen3-4B-Thinking-2507, Iteration=It192026.05 | 17.41 | |
| TMASBackbone=Qwen3-4B-Thinking-2507, Iteration=It172026.05 | 17.28 | |
| TMASBackbone=Qwen3-4B-Thinking-2507, Iteration=It112026.05 | 17.19 | |
| TMASBackbone=Qwen3-4B-Thinking-2507, Iteration=It92026.05 | 16.69 | |
| PaCoReBackbone=Qwen3-4B-Thinking-2507, Iteration=It112026.05 | 16.53 | |
| PaCoReBackbone=Qwen3-4B-Thinking-2507, Iteration=It192026.05 | 16.47 | |
| PaCoReBackbone=Qwen3-4B-Thinking-2507, Iteration=It172026.05 | 16.38 | |
| TMASBackbone=Qwen3-4B-Thinking-2507, Iteration=It32026.05 | 16.38 | |
| PaCoReBackbone=Qwen3-4B-Thinking-2507, Iteration=It32026.05 | 16.25 | |
| PaCoReBackbone=Qwen3-4B-Thinking-2507, Iteration=It92026.05 | 16.25 | |
| PaCoReBackbone=Qwen3-4B-Thinking-2507, Iteration=It12026.05 | 16.09 | |
| RSEBackbone=Qwen3-4B-Thinking-2507, Iteration=It12026.05 | 16.09 | |
| RSEBackbone=Qwen3-4B-Thinking-2507, Iteration=It32026.05 | 16.06 | |
| TMASBackbone=Qwen3-4B-Thinking-2507, Iteration=It12026.05 | 15.84 | |
| RSEBackbone=Qwen3-4B-Thinking-2507, Iteration=It192026.05 | 15.47 | |
| MV@64Backbone=Qwen3-4B-Thinking-2507, Iteration=It12026.05 | 15.4 | |
| RSEBackbone=Qwen3-4B-Thinking-2507, Iteration=It112026.05 | 14.47 | |
| V-RBackbone=Qwen3-4B-Thinking-2507, Iteration=It192026.05 | 14.41 | |
| V-RBackbone=Qwen3-4B-Thinking-2507, Iteration=It172026.05 | 13.81 | |
| RSEBackbone=Qwen3-4B-Thinking-2507, Iteration=It92026.05 | 13.66 | |
| Self-RefineBackbone=Qwen3-4B-Thinking-2507, Iteration=It112026.05 | 13.53 | |
| Self-RefineBackbone=Qwen3-4B-Thinking-2507, Iteration=It92026.05 | 13.47 | |
| Self-RefineBackbone=Qwen3-4B-Thinking-2507, Iteration=It192026.05 | 13.39 | |
| Self-RefineBackbone=Qwen3-4B-Thinking-2507, Iteration=It172026.05 | 13.31 | |
| V-RBackbone=Qwen3-4B-Thinking-2507, Iteration=It92026.05 | 12.78 | |
| V-RBackbone=Qwen3-4B-Thinking-2507, Iteration=It112026.05 | 12.59 | |
| RSEBackbone=Qwen3-4B-Thinking-2507, Iteration=It172026.05 | 12.59 | |
| Self-RefineBackbone=Qwen3-4B-Thinking-2507, Iteration=It32026.05 | 12.19 | |
| Self-RefineBackbone=Qwen3-4B-Thinking-2507, Iteration=It12026.05 | 12.12 | |
| V-RBackbone=Qwen3-4B-Thinking-2507, Iteration=It12026.05 | 11.47 | |
| V-RBackbone=Qwen3-4B-Thinking-2507, Iteration=It32026.05 | 10.66 |