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

Visual Question Answering on CareQA-V

74.63Accuracy

GPT-5.2

14.601230.185645.7761.3544Jun 25, 2026
Updated 27d ago

Evaluation Results

MethodLinks
2026.06
74.63
2026.06
64.71
2026.06
49.63
2026.06
48.53
2026.06
48.53
2026.06
45.59
2026.06
43.75
2026.06
43.38
2026.06
42.28
2026.06
40.44
2026.06
38.24
2026.06
36.76
2026.06
36.4
2026.06
31.25
2026.06
28.31
2026.06
26.47
2026.06
24.26
2026.06
21.32
2026.06
16.91