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

Mathematical Reasoning on DynaMath

81.42Accuracy

Gemini2.5-Pro

25.800840.240454.6869.1196May 20, 2025Jul 21, 2025Sep 21, 2025Nov 22, 2025Jan 23, 2026Mar 26, 2026May 28, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2026.03
81.42
2026.05
81.4
2026.05
80.1
2026.05
80
2026.03
79.5
2026.05
78.7
2026.05
78.4
2026.05
78
2026.03
77.41
2026.03
77.39
2026.05
76.4
2026.03
75.78
2026.03
75.54
2026.03
75.05
74.8
2026.05
74.1
2026.03
73.69
2026.05
73.4
2026.03
73.25
2026.03
73.2
2026.03
72.4
2026.03
72.19
2026.03
71.67
2026.03
71.38
2026.05
71.3
2026.03
71.22
2026.03
71
2026.03
69.4
2026.03
68.28
2026.03
68.12
2026.03
66.17
2026.03
65.44
2025.11
64.8
2025.11
63.7
2026.03
63.61
2026.03
62.37
2025.11
62.1
2025.11
61.8
2026.05
58
2026.05
57.8
2026.04
57.71
2026.05
57.7
2026.05
57.2
2026.04
57.11
2026.04
56.19
2026.04
55.96
2026.04
55.01
2025.05
55
2026.04
54.97
2025.11
54.9
2026.04
54.89
2026.04
54.84
2026.04
54.8
2025.11
54.7
2025.11
54.2
2025.11
53.8
2025.05
53.3
2025.10
53.3
2025.11
53.2
2025.11
52.4
2025.10
51.9
2025.11
51.8
2025.10
51.3
2025.10
51.2
2025.06
48.5
2026.04
48.45
2026.04
48.15
2026.04
47.82
2026.04
47.75
2026.04
47.3
2025.11
46.5
2026.04
45.86
2025.06
43.3
2025.11
42.7
2025.10
42.5
2025.10
41.9
2025.10
41.42
2025.10
40.7
2025.06
39.7
2025.10
39.3
2025.10
38.52
2025.10
37
2025.10
36.92
2025.10
36.72
2025.10
36.7
2025.10
36.23
2025.06
35.9
2026.05
35.4
2025.10
35.33
2025.11
34.3
2025.10
34.13
2025.10
33.63
2026.04
32.88
2025.10
30.3
2026.03
29.74
2025.10
29.3
2025.10
28.54
2025.10
28.5
2025.10
28.44
2026.03
27.94
Showing 100 of 127 rows