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

Multimodal Reasoning on MMBench

90.63Accuracy

AutoNPO

63.662870.663977.66584.6661Aug 8, 2024Nov 30, 2024Mar 24, 2025Jul 16, 2025Nov 7, 2025Mar 1, 2026Jun 23, 2026
Updated 25d ago

Evaluation Results

MethodLinks
2026.04
90.63-
2026.04
90.45-
2026.04
90.44-
2026.04
90.41-
2026.04
90.3-
2026.04
90.29-
89.79-
2026.04
89.49-
2025.11
89-
2026.02
87-
2025.11
86.9-
2025.11
84.2-
2026.06
83.6-
2026.05
83.5-
2026.05
83.4-
2026.05
83.3-
2026.02
82.9-
2026.05
82.9-
2024.08
82.7-
2024.08
82.5-
2025.11
82.5-
2026.05
80.8-
2024.09
80.4-
2024.09
79.2-
2025.10
78.52-
2025.10
78.09-
2025.10
77.84-
2024.09
76.6-
2024.09
76.1-
75.95-
2025.10
75.34-
2026.06
74.7-
2025.10
73.54-
2025.10
73.11-
2026.06
72.8-
2026.06
72.8-
2024.09
72.7-
2026.05
72-
2025.10
71.82-
2026.05
71.74-
2026.05
71.7-
71.53-
2026.05
70.86-
2026.05
70.82-
2024.09
70.8-
2026.02
70.7-
2026.05
70.51-
2026.05
70.19-
2026.05
70.12-
69.46-
2024.08
69.3-
2026.06
69.3-
2026.06
69.2-
2026.06
69.2-
2024.09
69.1-
2026.06
69.1-
2026.06
68.8-
2024.08
68.7-
2026.06
68.7-
2026.06
68.7-
2026.06
68.7-
2024.09
68.6-
2026.05
68.1-
2024.09
68-
2024.09
67.8-
2026.06
67.8-
2025.08
67.7-
2026.06
67.7-
2026.06
67.6-
2026.06
67.4-
2026.06
67.2-
2026.06
67.2-
2026.06
67.1-
2026.06
67-
2024.09
66.9-
2024.09
66.9-
2026.06
66.8-
2026.06
66.7-
2024.09
66.5-
2025.08
66.4-
2026.06
66.3-
2025.08
66.2-
2026.06
66.2-
2024.08
66.1-
2026.06
66.1-
2025.08
66-
2025.12
65.9-
2025.08
65.7-
2025.08
65.6-
2026.06
65.4-
2025.12
65.2-
2026.06
65-
2025.08
64.9-
2026.06
64.9-
2026.06
64.8-
2026.06
64.8-
2026.04
64.7-
2025.08
64.7-
2025.08
64.7-
2026.06
64.7-
Showing 100 of 266 rows