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

Multimodal Reasoning on MMBench EN V1.1

80.68Accuracy

WSVD-noQ

51.695259.220166.74574.2699May 30, 2026
Updated 1d ago

Evaluation Results

MethodLinks
2026.05
80.68
2026.05
80.68
2026.05
80.52
2026.05
80.16
2026.05
80.1
2026.05
80
2026.05
79.79
2026.05
79.12
2026.05
79.12
2026.05
78.29
2026.05
76.69
2026.05
76.35
2026.05
76.31
2026.05
75.43
2026.05
74.24
2026.05
73.92
2026.05
71.41
2026.05
70.06
2026.05
67.58
2026.05
67.53
2026.05
67.48
2026.05
67.38
2026.05
67.27
2026.05
67.27
2026.05
67.12
2026.05
67.09
2026.05
66.98
2026.05
66.91
2026.05
66.91
2026.05
66.86
2026.05
66.86
2026.05
66.51
2026.05
66.44
2026.05
66.44
2026.05
66.23
2026.05
66.18
2026.05
66.08
2026.05
65.14
2026.05
65.14
2026.05
65.09
2026.05
65.09
2026.05
64.99
2026.05
64.94
2026.05
64.88
2026.05
64.84
2026.05
64.83
2026.05
64.83
2026.05
64.83
2026.05
64.52
2026.05
64.51
2026.05
64.47
2026.05
64.36
2026.05
64.31
2026.05
64.26
2026.05
64.2
2026.05
64.1
2026.05
64.04
2026.05
63.95
2026.05
63.79
2026.05
63.64
2026.05
63.21
2026.05
62.96
2026.05
62.94
2026.05
62.74
2026.05
62.18
2026.05
62.08
2026.05
61.56
2026.05
61.56
2026.05
61.51
2026.05
61.45
2026.05
61.4
2026.05
61.25
2026.05
61.09
2026.05
61.04
2026.05
60.88
2026.05
60.82
2026.05
60.51
2026.05
60.48
2026.05
60.34
2026.05
60.21
2026.05
60.17
2026.05
60
2026.05
59.94
2026.05
59.79
2026.05
59.36
2026.05
59.3
2026.05
59.06
2026.05
58.64
2026.05
58.6
2026.05
58.39
2026.05
58.34
2026.05
57.87
2026.05
57.57
2026.05
57.47
2026.05
56.61
2026.05
56.56
2026.05
55.95
2026.05
55.9
2026.05
55.22
2026.05
52.81
Showing 100 of 125 rows