Mathematical Reasoning on AIME24 (Wall-clock time)
47.43Wall-clock Time (s)CGES-MARS
Evaluation Results
| Method | Links | |
|---|---|---|
| CGES-MARSBudget (B)=16, LLM batch size=12025.11 | 47.43 | |
| CGES-DeepConf (B10)Budget (B)=16, LLM batch size=1, DeepConf setting=B102025.11 | 47.9 | |
| CGES-LNS (geom)Budget (B)=16, LLM batch size=12025.11 | 51.57 | |
| DSCBudget (B)=16, LLM batch size=12025.11 | 54.86 | |
| CGES-LNS (arith)Budget (B)=16, LLM batch size=12025.11 | 66.31 | |
| CGES-DeepConf (tail)Budget (B)=16, LLM batch size=1, DeepConf setting=tail2025.11 | 73.68 | |
| ASC-βBudget (B)=16, LLM batch size=12025.11 | 83.65 | |
| ESCBudget (B)=16, LLM batch size=1, window size w=42025.11 | 90.8 | |
| ASC-DirBudget (B)=16, LLM batch size=12025.11 | 92.46 | |
| ESCBudget (B)=16, LLM batch size=1, window size w=82025.11 | 116.74 | |
| CGES-RMBudget (B)=16, LLM batch size=12025.11 | 124.64 | |
| SCBudget (B)=16, LLM batch size=12025.11 | 136.01 |