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

Vision Understanding on MMMU

72.9Accuracy

GPT-4o

25.5837.86550.1562.435Jun 3, 2025Jul 21, 2025Sep 7, 2025Oct 26, 2025Dec 13, 2025Jan 30, 2026Mar 20, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2025.06
72.9--
2025.06
67.8--
2025.06
58.6--
2025.06
58.6--
2025.06
55.3--
2025.06
50.6--
2026.03
50--
2026.03
50--
2026.03
49.9--
2026.03
48.9--
2026.03
48.8--
2026.03
48.8--
2026.03
48.8--
2026.03
47.8--
2026.03
47.8--
2026.03
47.8--
2025.12
45.8--
2025.12
45.1--
2026.03
44.4--
2025.12
43.9--
2025.12
43.6--
2026.03
43.3--
2026.03
42.3--
2026.03
42.2--
2026.03
42.2--
2026.03
41.8--
2026.03
41.7--
2025.12
41.3--
2026.03
41.3--
2025.12
40.2--
2026.03
39.6--
2026.03
38.9--
2025.12
38.4--
2025.12
37.9--
2026.03
37.8--
2025.12
36.9--
2026.03
36.8--
2026.03
36.7--
2026.03
36.7--
2025.12
36.6--
2025.06
36.3--
2025.12
36.3--
2026.03
36--
2026.03
35.3--
2025.12
35--
2026.03
34.9--
2026.03
34.7--
2025.12
33.3--
2025.12
33.3--
2026.03
33.3--
2025.06
32.8--
2026.03
32.2--
2026.03
32.2--
2025.06
31.6--
2026.03
31.4--
2025.06
30.5--
2026.03
30--
2025.12
29.9--
2026.03
28.9--
2026.03
28.9--
2026.03
28.9--
2026.03
28.9--
2025.12
28.8--
2026.03
27.8--
2025.06
27.4--
2025.05
-48.8-
2025.05
-31.6-
2025.05
-51.1-
2025.05
-41-
2025.05
-38.7-
2025.05
-41.8-
2025.05
-51.6-
2025.03
-23.6-
2025.03
-23.7-
2025.03
-18.4-
2025.03
-34.1-
2025.03
-29.6-
2025.03
-40.7-
2025.03
-14.8-
2025.03
-22.4-
2025.03
-26.3-
2025.03
-26.6-
2026.01
-48.8-
2026.01
-66.6-
2026.01
-58.6-
2026.01
-52.7-
2026.01
-48.9-
2026.01
-41-
2026.01
-58.6-
2026.01
-53.1-
2026.01
-55.3-
2026.01
-58.6-
2026.01
-67.4-
2025.12
--26.7
2025.12
--38.7
2025.12
--36.3
2025.12
--41
2025.12
--43.2
2025.12
--55.3
2025.12
--36.1
Showing 100 of 133 rows