List your company

Mathematical Reasoning on GSM8K (Performance %)

41.93PerformanceSPACE
14.78621.83328.8835.927Dec 8, 2025

Evaluation results

MethodLinks
SPACEIteration=Iter42025.1241.93
SPACEIteration=Iter32025.1240.94
SPACEIteration=Iter22025.1240.64
SPACEIteration=Iter12025.1240.56
SPACEIteration=Iter02025.1240.49
SPINIteration=Iter22025.1236.62
S-SimPOIteration=Iter02025.1234.33
SPINIteration=Iter32025.1233.59
S-IPOIteration=Iter12025.1232.26
SPINIteration=Iter42025.1231.69
S-SimPOIteration=Iter12025.1231.08
SPINIteration=Iter12025.1231.08
SPINIteration=Iter02025.1229.34
S-IPOIteration=Iter02025.1227.77
S-SimPOIteration=Iter32025.1226.31
Zephyr-7BIteration=N/A2025.1225.85
S-SimPOIteration=Iter22025.1225.8
S-SimPOIteration=Iter42025.1223.05
S-IPOIteration=Iter32025.1217.65
S-IPOIteration=Iter22025.1216.72
S-IPOIteration=Iter42025.1215.83