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

Multi-discipline Multimodal Understanding on MMMU Pro

67.3Accuracy

GPT-5-Mini

17.69230.57143.4556.329Aug 25, 2025Sep 26, 2025Oct 28, 2025Nov 29, 2025Dec 31, 2025Feb 1, 2026Mar 6, 2026
Updated 5d ago

Evaluation Results

MethodLinks
2025.12
67.3-
66-
65.3-
2025.12
65.2-
62.3-
61.6-
2025.12
61.4-
2025.12
61.4-
61.2-
2025.12
60.6-
2025.12
60.6-
2025.12
58.8-
2025.12
58.8-
58.1-
2025.12
58.1-
2025.12
57.2-
2025.12
57-
56.5-
2025.12
55.9-
2026.03
55.9-
2026.02
54.62-
54.4-
2025.12
53.2-
52.7-
2026.02
52.61-
52.4-
2026.02
52.29-
2026.02
52.17-
2026.02
51.98-
2025.12
51.9-
2026.02
51.67-
2026.02
51.6-
51.5-
2025.12
51.4-
2025.12
51-
46.9-
2026.02
46.7-
2025.12
46.3-
2025.12
46.2-
2026.02
42.43-
2026.02
41.99-
2025.12
41.3-
2026.03
40.2-
2025.12
40.1-
2026.01
39.8-
2026.03
39.7-
2025.12
39.5-
2025.12
38.5-
2025.12
38.3-
37.4-
2025.12
36.5-
2026.03
36.5-
2026.01
36.1-
35.3-
2025.12
31.6-
31-
2025.08
29.59-
2025.08
28.61-
2025.08
27.63-
2025.12
27.2-
2025.08
26.07-
2025.12
24.9-
2025.12
24.1-
2025.08
23.58-
2025.12
19.7-
2025.08
19.6-
2025.12
-49.7
2025.12
-44.4
2025.12
-48
2025.12
-40.3
2025.12
-14.7
2025.12
-18.5
2025.12
-18.9
2025.12
-16.8
2025.12
-18.7
2025.12
-26
2025.12
-25.3
2025.12
-18.6
2025.12
-25.8
2025.12
-26
2026.03
-54.5
2026.03
-50.1
2026.03
-38.3
2026.03
-38.2
2026.03
-35.5
2026.03
-33
2026.03
-34.8
2026.03
-32.2
2026.03
-42.9
2026.03
-40
2026.03
-42.4
2026.03
-39.6
2026.03
-40.9
2026.03
-43.8
2026.03
-42.9