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

Mathematical Problem Solving on MATH (Accuracy)

95.86Accuracy

INT4

-3.834422.047847.9373.8122Aug 21, 2025Oct 3, 2025Nov 16, 2025Dec 30, 2025Feb 12, 2026Mar 28, 2026May 11, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.04
95.86
2026.04
95.66
2026.04
95.59
2026.04
95.46
2026.04
95.32
2026.03
95.2
2026.03
94
2026.03
93.8
2026.03
93.6
2026.03
93.3
2026.04
92.71
2026.04
92.63
2026.04
92.59
2026.03
92.2
2026.04
92.18
2026.04
92.06
2026.03
91.6
2026.03
91.1
2026.03
89.6
2026.03
89
2026.03
88.4
2025.08
88.4
2025.08
88.4
2026.03
88.1
2026.03
88
2025.08
87.8
2026.03
87.5
2026.03
78.19
2026.03
75.5
2025.08
72.8
2026.03
71
2025.08
70.4
2026.03
69.42
2026.03
68.57
2025.08
66.8
2025.08
65.4
2025.08
62.8
2026.03
61.45
2026.03
59.5
2026.03
58.43
2026.03
53.51
2026.03
53.26
2025.08
53
2025.08
52
2025.08
51.8
2026.04
49.59
2026.05
48.34
2026.04
47.73
2026.03
45.14
2025.08
45
2025.08
43.8
2026.04
43.78
2026.04
42
2026.05
41.62
2026.04
41.35
2026.04
41.3
2025.08
39.8
2026.05
36.48
2025.08
34.4
2026.05
33.88
2026.04
31.46
2026.05
31.46
2026.05
31.14
2026.04
28.95
2026.04
28.12
2026.03
25.1
2026.05
25.08
2026.04
25.04
2026.05
25.03
2026.04
22.87
2026.05
22.57
2026.05
19.2
2026.05
16.21
2026.05
11.73
2026.04
0