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

Multimodal Evaluation on MMB

85.31Score

Baseline

34.027647.341360.65573.9687Jun 6, 2024Oct 9, 2024Feb 12, 2025Jun 18, 2025Oct 21, 2025Feb 24, 2026Jun 30, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.02
85.31------
2026.02
81.27------
2026.02
80.67------
2026.02
80.07------
2026.02
79.81------
2026.02
78.18------
2026.02
77.66------
2026.02
76.55------
2026.02
75.69------
2026.02
75.26------
2026.02
74.91------
2026.02
73.8------
2026.02
73.54------
2026.02
72.51------
2026.02
70.19------
2026.02
69.07------
2024.06
68.3------
2026.02
67.7------
2026.06
67.25-----98.4
2026.06
67.18-----99.4
2026.06
67.1-----100
2026.06
67.01-----98.2
2026.06
66.92-----96
2024.06
66.9------
2026.06
66.75-----86.5
2026.06
66.75-----98.8
2026.02
65.38------
2024.06
64.3------
2026.02
63.83------
2024.06
60.9------
2024.06
60.7------
2024.06
59.8------
2024.06
59.6------
2024.06
36------
2024.12
-5764.7716.40.116.1-
2024.12
-7290.318.40.128.4-
2024.12
-3850.8480.097-
2024.12
-1,2963.9811.50.194.7-
2024.12
-4141.988.70.115.1-
2024.12
-900.097.60.0511.7-