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

Visual Reasoning on MMVP

86.3Accuracy

GPT-4o

22.23638.86855.572.132Jun 13, 2024Sep 26, 2024Jan 10, 2025Apr 26, 2025Aug 9, 2025Nov 23, 2025Mar 9, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.06
86.3
2024.06
85.3
2026.01
74
2024.06
73.3
2026.01
72.67
2026.01
72.67
2026.01
72
2024.06
71
2026.01
70
2026.01
68.7
2026.01
68.67
2026.01
68
2026.01
65.67
2026.01
64
2026.01
57.67
2024.06
49.3
2026.03
47.2
2026.03
46.6
2026.03
46.5
2026.03
46.3
2026.03
45
2026.03
44.5
2026.03
44
2026.03
43.2
2026.03
43
2026.03
42.9
2026.03
42
2026.03
42
2024.06
40.7
2026.03
40
38.7
24.7