Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Math Reasoning on MATH 500 (Pass@1, #Tokens)

95.2Pass@1

ReBalance

65.87273.48681.188.714Mar 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
95.23,662
2026.03
94.84,535
2026.03
94.83,912
2026.03
94.43,179
2026.03
94.24,176
2026.03
943,641
2026.03
93.84,470
2026.03
93.82,950
2026.03
93.82,657
2026.03
93.84,063
2026.03
93.83,516
2026.03
93.82,879
2026.03
93.83,830
2026.03
93.43,727
2026.03
93.23,144
2026.03
932,825
2026.03
92.83,219
2026.03
92.62,903
2026.03
92.63,536
2026.03
90.62,843
2026.03
903,127
2026.03
89.83,699
2026.03
88.42,239
2026.03
88.22,723
2026.03
87.82,367
2026.03
86.82,479
2026.03
833,474
2026.03
80.6834
2026.03
80.23,512
2026.03
79.64,516
2026.03
78.63,259
2026.03
78.63,458
2026.03
782,645
2026.03
77.23,694
2026.03
751,582
2026.03
672,251