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

Multimodal Understanding on MMMU (Score)

81.8MMMU Score

GPT-5-Thinking

26.78441.06755.3569.633May 23, 2025Jul 27, 2025Sep 30, 2025Dec 4, 2025Feb 7, 2026Apr 13, 2026Jun 18, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2025.09
81.8
2026.04
76.3
2025.09
74.7
2026.04
73.4
2026.04
72.42
2026.04
70.8
70.6
2026.04
69.6
2026.04
69.1
2026.03
68.9
2026.04
67.6
2026.06
64.6
2026.04
63.3
2026.04
63.3
2026.06
63.2
2026.06
63
2026.06
62.7
2026.06
61.4
2026.06
60.8
2025.09
60.2
2025.09
59.1
2026.03
58.6
58.6
2025.11
58.6
2025.05
58.6
2025.09
57.6
2026.04
57.4
2025.09
56.2
2025.05
56
2025.09
55.6
2026.03
55.3
2025.11
55.3
2026.03
54.7
2025.09
54.3
53.2
2026.03
53.1
2025.11
53.1
53.1
2025.09
52.7
52.4
2026.05
52.3
2026.05
51.9
2026.05
51.9
2026.06
51.8
2026.03
51.1
2026.03
50.6
2025.11
50.6
2026.06
49.8
2026.03
48.9
2025.05
48.8
2026.05
47.9
2025.05
46.7
2026.05
46
2026.03
44.2
2025.11
43.8
2025.11
43.2
2026.03
41.9
2026.05
41.7
2025.11
41.2
2026.03
41
2025.11
41
2026.05
40.7
2026.05
39.7
2026.05
39.6
2025.09
38.7
2025.09
38.2
2026.05
37.9
2026.05
37.1
2026.05
37
2025.09
36.3
2026.05
36.2
2026.05
35.9
2025.05
35.8
2025.11
35.7
2025.11
35.6
2026.05
35.6
2025.09
35.4
2025.09
35.4
2026.03
35
2026.05
34.9
2026.05
34.4
2025.09
34.3
2026.03
34.11
2026.03
34.1
2026.05
34.1
2026.05
34
2026.05
33.6
2026.03
33.56
2025.05
33.2
2026.05
32.7
2026.05
31.7
2025.11
31.6
2025.09
31.6
2026.05
31.6
2026.05
31.4
2025.09
30.7
2025.09
30.5
2026.05
29.2
2026.05
29
2026.05
28.9
Showing 100 of 110 rows