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

Visual Question Answering on RealWorldQA xAI 2024 (test)

72.81Accuracy

Robust-U1

37.325246.537655.7564.9624Jun 6, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
72.81
2026.06
72.81
2026.06
71.5
2026.06
68.76
2026.06
67.84
2026.06
67.71
2026.06
67.46
2026.06
67.05
2026.06
66.4
2026.06
65.75
2026.06
65.22
2026.06
64.96
2026.06
63.39
2026.06
63.26
2026.06
63.14
2026.06
60.65
2026.06
58.16
2026.06
57.64
2026.06
57.38
2026.06
55.42
2026.06
54.9
2026.06
54.77
2026.06
53.72
2026.06
52.81
2026.06
43.26
2026.06
42.61
2026.06
42.48
2026.06
41.43
2026.06
40
2026.06
39.73
2026.06
39.47
2026.06
38.69