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

Accuracy on Mathematical Reasoning on MathVista

82.1Accuracy (MathVista Reasoning)

Octopus

65.04469.47273.978.328Jul 8, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2026.07
82.1
2026.07
81.2
2026.07
75.8
2026.07
74.4
2026.07
72.6
2026.07
72.3
2026.07
71.6
2026.07
71.2
2026.07
71
2026.07
70.6
2026.07
69.7
2026.07
68.2
2026.07
65.7