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

Medical Visual Question Answering on MMMU Health & Medicine (test)

74.5Accuracy

OpenAI-o3

25.137.92550.7563.575Nov 27, 2025Dec 19, 2025Jan 10, 2026Feb 2, 2026Feb 24, 2026Mar 18, 2026Apr 10, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.04
74.5
2026.04
73.6
2026.04
72.8
2026.04
70.7
2026.04
62.3
2026.04
60.1
2026.04
60.1
2025.11
59.7
2026.04
58.9
2026.04
58
2026.04
57.8
2026.04
57.4
2026.04
56.6
2026.04
56.6
2026.04
52.9
2025.11
52.7
2025.11
51.2
2025.11
49.5
2026.04
49.3
2025.11
49.1
2025.11
47.5
2026.04
46.4
2026.04
45.9
2026.04
44.7
2026.04
44.1
2026.04
42.9
2026.04
40.1
2026.04
40.1
2026.04
38.8
2026.04
38.2
2025.11
36.9
2025.11
35.5
2025.11
34.3
2026.04
33.1
2025.11
32.7
2025.11
28.3
2026.04
28.3
2025.11
27
2026.04
27