Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-discipline Multimodal Understanding on MMMU (val)

81.7Accuracy

gemini-2.5-pro-exp-03-25

39.47650.43861.472.362Nov 6, 2023Mar 22, 2024Aug 7, 2024Dec 23, 2024May 9, 2025Sep 24, 2025Feb 9, 2026
Updated 2d ago

Evaluation Results

MethodLinks
81.7--
2026.01
79.2--
2026.02
78.78--
2026.02
78.2--
2026.02
74.44--
2026.02
72.4--
2026.01
72.2--
2026.02
72.11--
2026.02
71.8--
2026.02
71.4--
2026.02
71.2--
2026.02
71--
2026.02
70.8--
70.7--
70.7--
2026.02
70.6--
2026.02
70.4--
2026.01
70.2--
2026.02
69.7--
2026.02
69.4--
2024.09
69.2--
2024.08
69.1--
2024.12
69.1--
2026.02
69.1--
2026.02
67.4--
2026.02
67.33--
2026.02
66.7--
2026.01
64.9--
2026.02
64.6--
2026.02
62.44--
62.2--
2026.02
62--
2026.02
61.33--
2026.02
61--
2024.09
60.6--
60--
2024.04
59.4--
2024.04
59.4--
2026.02
59.33--
2026.01
58.6--
2024.04
58.5--
2026.02
57.89--
2024.03
56.8--
2024.04
56.8--
2024.08
56.8--
2024.08
56.8--
2024.12
56.8--
2026.02
56.67--
2024.12
54.1--
2024.12
54.1--
2024.09
53.8--
2024.04
53.1--
2026.02
53--
2024.04
51.6--
2026.02
51.44--
2024.04
51.3--
2026.02
51.11--
2024.03
51.1--
2024.04
51.1--
2024.09
51.1--
2024.12
50.9--
2024.04
50.2--
2024.04
49.9--
2024.09
49.7--
2024.12
49.3--
2024.08
48.8--
2024.12
48.8--
2024.12
48.8--
2024.03
48.7--
2024.03
48--
2024.04
48--
2024.03
47.9--
2024.04
47.9--
2024.09
47.4--
2024.12
47.3--
2026.02
46.89--
2024.03
45.2--
2024.04
45.2--
2024.04
45.2--
2024.04
44.7--
2024.09
44.7--
2024.12
44.1--
2024.12
43.9--
2024.12
43.9--
2024.12
43.4--
2024.12
43.3--
2024.09
43--
2024.09
42.9--
2024.12
42.9--
2024.12
42.7--
2024.12
42.6--
2024.12
41.9--
2024.03
41.8--
2024.09
41.8--
2024.09
41.4--
2024.12
41.3--
2024.09
41.2--
2024.09
41.2--
2023.11
41.1--
2024.03
41.1--
Showing 100 of 254 rows