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

Multimodal Mathematical Reasoning on MathVista (GEO, ALG, GPS, MWP, ALL)

78.2Overall Accuracy (ALL)

Vision-R1-72B*

45.33653.86862.470.932Mar 9, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.03
78.288.386.889.479.6
2025.03
76.485.882.68878.5
2025.03
73.9----
2025.03
73.577.877.978.874.7
2025.03
73.580.37983.280.6
2025.03
72.972.873.77572.6
2025.03
71.976.676.577.975.8
2025.03
68.166.968.766.876.9
2025.03
67.7----
2025.03
63.8----
2025.03
63.1----
2025.03
59.8--79.375.3
2025.03
54.8----
2025.03
50--66.861.8
2025.03
49.9----
2025.03
47.947.3-48.1-
2025.03
46.656.540.257.756.5