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

STEM & Puzzle on MMMU (val)

79.7Accuracy

M2Note

50.89258.37165.8573.329Jan 29, 2026Feb 23, 2026Mar 21, 2026Apr 15, 2026May 11, 2026Jun 5, 2026Jul 1, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2026.07
79.7
2026.01
79
2026.01
78.1
2026.07
77.9
2026.07
77.9
2026.01
77.7
2026.07
77.1
2026.01
76
2026.01
74.1
2026.01
71.3
2026.01
69.6
2026.07
69.4
2026.07
69.1
2026.07
68.9
2026.07
68.8
2026.07
68.4
2026.07
67.1
2026.07
67.1
2026.01
63.1
2026.01
62.8
2026.07
58.8
2026.01
57.8
2026.07
54.9
2026.01
54.8
2026.07
52.4
2026.07
52