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

General Visual Understanding on MMMU

75.1Accuracy

Claude4-Sonnet

21.95635.75349.5563.347Aug 27, 2025Oct 9, 2025Nov 21, 2025Jan 3, 2026Feb 15, 2026Mar 30, 2026May 13, 2026
Updated 12d ago

Evaluation Results

MethodLinks
75.164.1
2026.02
70.261.9
2026.02
69.1164.39
2026.02
69.156.1
2026.02
67.953.8
2026.05
57.1-
2026.05
56.1-
2026.05
55.5-
2026.05
55.2-
2026.05
55-
2025.08
52.252.2
2025.08
51.850.7
2026.05
51.5-
2026.05
51-
2026.05
50.7-
2026.05
50.5-
2025.08
49.648.8
2025.08
49.547.1
2025.08
49.549.5
2025.08
47.346
2025.08
45.644.4
2026.05
43.2-
2025.08
42.844.5
2026.05
42.8-
2026.05
41.2-
2026.05
41-
2025.08
40.945.2
2026.05
40.9-
2026.05
40.4-
2025.08
33.541.5
2026.05
33.3-
2025.08
30.633.9
2026.05
30.6-
2025.08
25.535.5
2026.05
24-
2026.05
-49.1
2026.05
-48.7
2026.05
-49.3
2026.05
-52.9
2026.05
-52.7
2026.05
-50.9
2026.05
-51.5