List your company

Grade School Math Reasoning on GSM8K (Accuracy, #Calls)

94.9AccuracyCGES-RM
93.8694.1394.494.67Nov 4, 2025

Evaluation results

MethodLinks
CGES-RMBudget (B)=162025.1194.91.25
SCBudget (B)=162025.1194.216
ESCBudget (B)=16, Window size (w)=42025.1194.25.16
ESCBudget (B)=16, Window size (w)=82025.1194.29.41
ASC-βBudget (B)=162025.1194.25
ASC-DirBudget (B)=162025.1194.25.17
CGES-MARSBudget (B)=162025.1194.23.11
CGES-LNS (arith)Budget (B)=16, Aggregation function=arith2025.1194.12.41
CGES-LNS (geom)Budget (B)=16, Aggregation function=geom2025.1194.13.04
CGES-DeepConf (B10)Budget (B)=16, DeepConf variant=B102025.1194.12.41
CGES-DeepConf (tail)Budget (B)=16, DeepConf variant=tail2025.1194.12.41
DSCBudget (B)=162025.1193.92.85