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

Multimodal Reasoning on MMBench

88.15Overall Score

Qwen2.5-VL

22.78639.755556.72573.6945Nov 27, 2023Apr 19, 2024Sep 10, 2024Feb 1, 2025Jun 25, 2025Nov 16, 2025Apr 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.03
88.15-
2026.03
87.48-
2026.03
84.62-
84.36-
2026.03
84.27-
84.11-
2025.12
83.36-
2026.03
82.9-
2026.03
82.8-
2026.03
82.6-
2025.12
82.59-
2025.01
82.4-
2026.03
81.7-
2026.03
81.53-
2026.03
80.8-
2025.12
80.56-
2025.12
79.96-
2025.01
79.89-
2026.03
78.6-
2025.01
77.4-
2026.03
77.2-
2025.01
76.9-
2025.01
76.8-
2026.03
76.6-
2026.03
76.46-
2023.11
76.3-
2025.01
76.3-
2026.03
75.9-
2025.01
75.7-
2026.03
75.51-
2023.11
75.5-
2025.01
75.4-
2026.03
75.4-
2025.01
75.34-
2025.01
75.3-
2025.01
75-
2026.03
74.9-
2026.03
74.9-
2023.11
74.8-
2026.03
73.2-
2026.03
73.2-
2026.03
72.3-
2025.01
71.5-
2026.03
71-
2023.11
70.7-
2026.03
69.93-
2026.03
69.6-
2026.04
69.6-
2023.11
68.3-
2024.02
67.6-
2024.02
67.4-
2026.03
67.4-
2023.11
67-
2024.02
66.8-
2023.11
66-
2026.04
66-
2023.11
65.9-
2025.01
65.8-
2023.11
65.5-
2024.02
65.4-
2026.04
65.2-
2024.02
65.1-
2023.11
64.5-
2026.04
64.4-
2026.04
64.3-
2026.04
63.9-
2026.04
63.4-
2026.04
63.1-
2026.03
62.5-
2023.11
61.2-
2026.04
60.9-
2024.02
60.1-
2026.04
56.3-
2026.04
49.1-
2026.04
43.4-
2023.11
40.3-
2023.11
36-
2023.11
25.3-
2024.02
-50.85
2024.02
-56.46
2024.02
-59.78
2024.02
-57.06
2024.02
-59.1
2024.09
-59.6
2024.09
-63.2
2024.09
-68
2024.09
-59.8
2024.09
-66.5
2024.09
-66.9
2024.09
-68.6
2024.09
-66.9
2024.09
-64.1
2024.09
-69.1
2024.09
-67.8
2024.09
-70.8
2024.09
-64
2024.09
-64.6
2024.09
-62.8
2024.09
-79.2
2024.09
-80.4
Showing 100 of 133 rows