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

Visual Question Answering on MMMU

81.7Accuracy

Gemini 2.5 Pro

22.10837.57953.0568.521Mar 23, 2026Apr 5, 2026Apr 18, 2026May 1, 2026May 14, 2026May 27, 2026Jun 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
81.7-
2026.03
76.4-
76-
2026.04
71.6-
2026.03
70.8-
2026.04
70.7-
2026.04
70.6-
70.1-
2026.04
69.8-
2026.04
69.7-
2026.04
67.9-
2026.04
60.92-
2026.04
60.2-
2026.04
59.78-
2026.04
58.8-
2026.04
57.3-
2026.04
56.7-
2026.04
55.8-
2026.04
55.33-
2026.04
54.78-
2026.04
54.78-
2026.04
54.67-
2026.04
54.56-
2026.04
54.44-
2026.04
54.22-
2026.04
54.22-
2026.04
54.11-
2026.04
54.11-
2026.04
53.78-
2026.04
53.4-
2026.04
53.22-
2026.04
51.89-
2026.06
49.6-
2026.06
48.7-
2026.06
48.4-
2026.06
48.1-
2026.06
48.1-
2026.06
47.3-
2026.06
47-
2026.06
46.7-
2026.06
45.8-
2026.06
45.4-
2026.06
45.3-
2026.06
45.1-
2026.06
45-
2026.06
45-
2026.06
44.9-
2026.06
44.6-
2026.06
44.4-
2026.06
44.3-
2026.06
44.3-
2026.06
44.3-
2026.06
43.3-
2026.06
43.2-
2026.06
42.8-
2026.06
42.3-
2026.06
41.7-
2026.06
41.2-
2026.06
37.996.9
2026.03
36.61-
2026.06
36.697.9
2026.03
36.4-
2026.06
36.495.8
2026.03
36.38-
2026.06
36.3100
2026.06
36.294.7
2026.06
36.293.2
2026.06
36.199.8
2026.06
35.996.7
2026.03
35.82-
2026.03
35.8-
2026.06
35.898.4
2026.06
35.892.1
2026.03
35.72-
2026.06
35.7100.6
2026.03
35.67-
2026.03
35.52-
2026.06
35.599.2
2026.06
35.491.5
2026.03
35.14-
2026.03
35.05-
2026.06
34.985.2
2026.03
34.68-
2026.03
34.59-
2026.03
34.4-
2026.06
34.390.1
2026.03
34.27-
2026.06
34.293.8
2026.06
34.195.7
2026.06
3477.9
2026.06
33.895.4
2026.06
33.892.9
2026.03
33.75-
2026.03
33.01-
2026.03
32.79-
2026.03
32.15-
2026.03
31.9-
2026.03
31.66-
2026.06
26.570.3
2026.05
24.4-
Showing 100 of 101 rows