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

Multimodal Reasoning on MMMU (test)

64.7Accuracy

GPT-4o

20.55232.013543.47554.9365Dec 6, 2024Feb 17, 2025May 1, 2025Jul 14, 2025Sep 25, 2025Dec 7, 2025Feb 19, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
64.7
2024.12
61.8
2024.12
57.6
2024.12
55.1
2024.12
54.6
2024.12
51.8
2025.08
50.44
2024.12
49.3
2024.12
48.9
2024.12
46.9
2026.01
46.6
2024.12
46.3
2026.01
44.6
2026.01
44.4
2024.12
44.3
2024.12
43.8
2026.01
42.8
2026.01
42.6
2024.12
41.4
41
2024.12
38.2
2024.12
35.8
2024.12
34.7
2025.08
33.67
2024.12
32.8
2025.08
32.22
2026.02
30
2026.02
29.3
2026.02
28
2026.02
27.3
2026.02
27.3
2026.02
26.7
2026.02
25.3
2025.08
22.25