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

Fine-grained Visual Reasoning on V-Star

95.7Overall Accuracy

o3 OpenAI

64.81272.83180.8588.869Jul 1, 2026
Updated 23d ago

Evaluation Results

MethodLinks
2026.07
95.7--
2026.07
93.792.296.1
2026.07
93.292.294.7
2026.07
90.693.985.5
2026.07
90.191.388.2
2026.07
86.986.188.2
2026.07
84.384.384.2
2026.07
83.884.382.9
2026.07
82.283.580.3
2026.07
81.779.185.5
2026.07
81.28082.9
2026.07
80.683.576.3
2026.07
74.97377.6
2026.07
66--