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

Math Reasoning on MATH (test) (Accuracy)

96Accuracy

MAD

-1.2424.00549.2574.495May 17, 2025Jul 15, 2025Sep 13, 2025Nov 11, 2025Jan 10, 2026Mar 10, 2026May 9, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
96
2026.05
95.6
2026.05
95
2026.05
94.6
2026.05
91.6
2026.05
90.8
2026.05
90.4
2026.05
90.4
2026.05
88.8
2026.04
83.6
2026.04
82.1
2026.05
81.6
2026.04
80.3
2026.04
80.2
2026.04
79.6
2026.04
79.5
2026.04
79
2026.04
78.9
2026.04
78.6
2026.04
77.8
2026.04
77.6
2026.04
76.3
2026.04
75.1
2026.04
74.8
2026.04
74.6
2026.04
74.1
2026.04
72.8
2026.04
72
2026.04
71.9
2026.04
71.7
2026.04
71.3
2026.04
70.4
2026.04
67.3
2026.04
65.8
2026.02
46.8
2025.05
35.17
2025.05
34.91
2025.05
33.95
2025.05
33.7
2025.05
33.41
2025.05
33.34
2025.05
32.49
2025.05
32.35
2025.05
29.42
2025.05
28.94
2025.05
28.72
2026.02
25
2026.02
21
2026.02
18
2026.02
15.8
2026.02
14.2
2026.02
13.6
2026.03
4.44
2026.03
4.42
2026.03
4.18
2026.03
3.97
2026.03
3.86
2026.03
3.84
2026.03
2.5