Mathematical Reasoning on AIME24 (Accuracy and #Calls)
77.7AccuracyCGES-LNS (arith)
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CGES-LNS (arith)Budget (B)=16, Aggregation function=arith2025.11 | 77.7 | 7.77 | |
| CGES-DeepConf (B10)Budget (B)=16, DeepConf variant=B102025.11 | 77.7 | 5.62 | |
| SCBudget (B)=162025.11 | 77.3 | 16 | |
| ESCBudget (B)=16, Window size (w)=42025.11 | 77.3 | 10.68 | |
| ESCBudget (B)=16, Window size (w)=82025.11 | 77.3 | 13.73 | |
| ASC-βBudget (B)=162025.11 | 77.3 | 9.84 | |
| ASC-DirBudget (B)=162025.11 | 77.3 | 10.88 | |
| CGES-LNS (geom)Budget (B)=16, Aggregation function=geom2025.11 | 77.3 | 6.05 | |
| CGES-MARSBudget (B)=162025.11 | 77.3 | 5.2 | |
| CGES-DeepConf (tail)Budget (B)=16, DeepConf variant=tail2025.11 | 77 | 8.64 | |
| DSCBudget (B)=162025.11 | 74.3 | 6.43 | |
| CGES-RMBudget (B)=162025.11 | 66.7 | 13.6 |