Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Mathematical Reasoning on MATH 500 (Acc, #Tok, LR)

95Accuracy

NEAT

80.33684.14387.9591.757Feb 2, 2026
Updated 3d ago

Evaluation Results

MethodLinks
2026.02
953,90624
2026.02
94.65,140-
2026.02
94.62,99234.3
2026.02
94.53,23528.9
2026.02
94.14,551-
2026.02
93.73,38925.5
2026.02
93.33,50731.8
2026.02
92.33,88524.4
2026.02
92.23,743-
2026.02
92.22,91422.1
2026.02
922,84424
2026.02
91.73,84125.3
2026.02
91.71,95657
2026.02
89.62,27239.3
2026.02
89.12,65729
2026.02
88.71,93562.4
2026.02
87.11,23975.7
2026.02
8785381.3
2026.02
85.74,087-
2026.02
853,58512.3
2026.02
84.73,25420.4
2026.02
84.72,93428.2
2026.02
84.43,66719.4
2026.02
843,54113.4
2026.02
83.32,40541.2
2026.02
82.32,72233.4
2026.02
81.82,07044.7
2026.02
80.91,17365.4