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

General Visual Reasoning on MMMU

69.1Accuracy

GPT-4o

42.247249.218656.1963.1614Feb 25, 2026Mar 12, 2026Mar 28, 2026Apr 12, 2026Apr 28, 2026May 13, 2026May 29, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
69.1-
68.3-
2026.05
66.461.12
2026.05
65.34-
2026.05
59.010.38
2026.05
58.63-
2026.05
58.63-
2026.02
57.44-
2026.02
56.98-
2026.02
56.67-
2026.02
55.44-
2026.02
54.67-
2026.02
54.29-
2026.02
53.78-
2026.05
53.66-
2026.02
53.11-
2026.05
52.79-
2026.02
51-
2026.05
48.39-
2026.02
45.73-
2026.02
43.7-
2026.02
43.28-