Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multimodal Reasoning on MMMU (val)

75Accuracy

Claude-Sonnet-3.7

37.76847.43457.166.766Jul 31, 2024Nov 1, 2024Feb 2, 2025May 7, 2025Aug 8, 2025Nov 9, 2025Feb 11, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2025.12
75
2025.12
74.1
2025.12
72.6
2025.12
71.4
2025.12
71.2
2025.12
71
2025.12
70.8
2025.12
70.2
2024.12
70.1
2025.12
69.9
2025.12
69.6
2024.07
69.1
69.1
2024.07
68.3
68.3
2025.12
68.1
2025.12
67.4
2025.12
66.7
2025.12
64.6
2024.07
64.5
2024.12
64.5
2024.12
63.9
2024.12
63.1
2024.12
62.7
2025.12
62.5
2024.07
62.2
2025.12
62.2
62.2
2025.12
61.6
2025.12
61.3
2025.12
61.1
2024.07
60.6
2024.12
60
2024.12
59.7
2025.12
57.4
2025.12
57.1
2026.01
57
2026.01
56.89
2024.12
56.8
2025.12
56.7
2024.07
56.4
2025.12
56
2024.12
56
2025.12
55.7
2026.01
55.44
2025.12
55.4
2026.01
55.22
2025.12
55.2
2024.12
55.2
2024.12
55.1
2024.12
55
2025.12
54.7
2025.12
54.3
2025.12
54.1
2024.12
54.1
2024.12
54.1
2025.05
52.78
2024.12
52.6
2026.02
52.56
2025.12
52.5
2025.12
52.3
2024.12
52.3
2026.01
52.22
2025.12
52.2
2026.02
51.89
2026.02
51.67
2026.01
51.44
2025.12
51.2
2024.12
51.2
2026.02
50.33
2026.02
50.11
49.8
2024.12
49.7
2024.07
49.6
2025.12
49.6
2026.01
49.44
2025.12
49.2
2025.12
48.8
2025.05
48.67
2026.02
48.56
2026.01
48.44
2026.01
48.11
2024.12
47.9
2025.05
47.89
2026.02
47.45
2026.02
47.45
2024.12
47.4
2025.12
47.2
46.8
2025.12
46.4
2025.12
46.3
2025.12
44.5
2025.12
44
2024.12
43.6
2025.12
43
2024.12
43
2025.12
42
2024.12
41.1
2024.12
40.9
2025.03
39.2
Showing 100 of 114 rows