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

Mathematical Reasoning on AQuA (Accuracy)

91.8Accuracy

CLoT

9.01630.5085273.492Oct 3, 2025Nov 3, 2025Dec 4, 2025Jan 5, 2026Feb 5, 2026Mar 8, 2026Apr 9, 2026
Updated 8d ago

Evaluation Results

MethodLinks
2026.04
91.8
2026.04
88.1
2026.04
87.4
2026.04
86.9
2026.04
86.6
2026.03
86.45
2026.04
85.8
85.51
2026.04
84.2
2026.04
84.2
2026.04
83.7
83.46
2025.10
83.46
2026.04
83.3
2026.04
83.1
2026.04
83.1
2026.04
82.7
2026.04
82.7
2026.03
81.6
2026.04
81.4
80.94
2026.03
80.51
2025.10
79.92
2026.04
79.9
2026.04
79.5
2025.10
79.13
2026.03
77.65
2026.04
77.5
2026.03
76.48
2026.03
75.63
2026.03
74.05
2026.03
73.58
2026.03
72.95
2026.03
71.23
2026.03
71.06
2025.10
68.5
2025.10
55.51
2025.10
48.43
2026.04
41.34
2026.03
38.9
2026.04
36.61
2026.04
36.22
2026.04
35.96
2026.04
34.65
2026.04
33.86
2026.04
33.07
2026.03
32.7
2026.04
32.68
2026.03
31.5
2026.04
29.13
2026.03
26.8
2026.03
26.4
2026.04
26.19
2026.04
25.98
2026.04
25.72
2026.04
25.2
2026.04
24.41
2026.03
24
2026.04
23.62
2026.04
23.62
2026.04
23.23
2026.03
23
2026.04
21.65
2026.04
21.26
2026.04
20.08
2026.04
19.69
2026.04
19.68
2026.04
18.9
2026.03
15.9
2026.03
15.6
2026.03
15.2
2026.04
15.16
2026.03
14.8
2026.04
13.78
2026.04
12.99
2026.04
12.99
2026.04
12.6
2026.04
12.2