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

Math Reasoning on MATH 500 (Acc., Tok., AES)

94.4Accuracy

DEPO

13.59234.57155.5576.529Jan 21, 2026Feb 2, 2026Feb 15, 2026Feb 27, 2026Mar 12, 2026Mar 24, 2026Apr 6, 2026
Updated 10d ago

Evaluation Results

MethodLinks
2026.02
94.42,3180.43
2026.02
93.81,7000.59
2026.02
931,7280.55
2026.02
92.81,3000.66
2026.02
92.42,2520.39
2026.02
92.21,8360.5
2026.02
92.13,1870.12
2026.02
923,5930
2026.02
921,8750.48
2026.02
921,6580.54
2026.02
91.61,4050.59
2026.02
91.22,1460.36
2026.02
90.41,5680.48
2026.02
89.82,0440.31
2026.02
87.22,7620.69
2026.04
87.25,424-
2026.04
86.66,350-
2026.04
86.26,032-
2026.02
861,3180.9
2026.02
85.81,9150.79
2026.04
85.810,468-
2026.04
85.84,420-
2026.02
84.41,8170.76
2026.04
84.44,987-
2026.02
84.21,8720.74
2026.02
842,1950.67
2026.04
845,245-
2026.04
845,224-
2026.04
83.83,315-
2026.02
83.51,9490.7
2026.04
83.45,418-
2026.04
83.42,742-
2026.02
83.21,9380.69
2026.04
83.25,543-
2026.04
83.23,018-
2026.02
833,0610.48
2026.04
82.83,573-
2026.04
82.83,686-
2026.02
82.52,2330.61
2026.02
82.15,5340
2026.02
821,7820.67
2026.04
824,951-
2026.02
81.72,5970.51
2026.02
811,6790.63
2026.04
813,697-
2026.04
812,326-
2026.04
812,229-
2026.04
80.52,226-
2026.04
802,322-
2026.04
78.61,746-
2026.01
40.7--
24.7--
2026.01
23.2--
20.8--
20.6--
2026.01
20.2--
2026.01
19.1--
2026.01
17.9--
2026.01
17--
2026.01
16.7--