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

Spatial Reasoning on MMVP

85.33Accuracy

GPT-4o

39.923651.711863.575.2882Nov 10, 2025Dec 19, 2025Jan 27, 2026Mar 8, 2026Apr 16, 2026May 25, 2026Jul 4, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
85.33
2026.07
82.33
2026.07
81.67
2026.07
81.33
2025.11
79.7
2026.07
78.67
2025.11
78
2025.11
77.9
2026.07
77
2026.07
75.67
2025.11
75.3
2025.11
74.3
2025.11
72.3
2025.11
71.3
2025.11
71.3
2025.11
70.7
2025.11
70.3
2025.11
69
2025.11
68.3
2025.11
68.3
2025.11
67.7
2025.11
67
2025.11
66.3
2025.11
64
2026.07
63.33
2025.11
63
2025.11
62.7
2025.11
61.7
2026.07
41.67