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

Visual Mathematical Reasoning on MathVista (testmini)

79.3Accuracy

VisRef

23.45237.95152.4566.949Dec 5, 2024Feb 24, 2025May 17, 2025Aug 6, 2025Oct 27, 2025Jan 16, 2026Apr 8, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2026.02
79.3------------
2026.02
78.2------------
2026.02
77.1------------
2026.02
74.2------------
2026.02
74.1------------
2026.02
73.9------------
2026.02
73.8------------
2026.02
73.1------------
2026.02
68.1------------
67.7------------
2024.12
67.5------------
2026.04
67.5------------
2024.12
66.1------------
2024.12
65.4------------
2025.06
65.469.1451.4475.8166.4664.2554.4567.4253.5627.0360.4268.0377.74
2024.12
65.2------------
2024.12
64.5------------
2025.06
64.568.0356.7372.0467.0958.159.4362.6158.1629.7350.6967.2175.75
2026.04
64.1------------
63.9------------
2024.12
63.8------------
2024.12
63.7------------
2024.12
63.2------------
2026.04
63.1------------
2026.04
62.5------------
2025.06
62.370.6348.0869.8963.9256.9851.660.3450.6310.8151.3960.6679.07
2024.12
61.7------------
2026.04
60.3------------
2025.06
60.266.5453.3763.4461.3954.1954.855.2454.3913.5143.7557.3874.09
2026.04
60------------
2025.06
58.663.5748.0862.961.3956.4250.8955.8149.3721.6245.8360.6670.43
2024.12
58.3------------
2024.12
58.2------------
2024.12
58------------
2025.06
57.767.6644.7159.6858.8654.7548.7554.9646.0313.5143.0656.5675.42
2024.12
57.3------------
2025.06
55.760.5948.5660.7556.9650.2849.1152.6946.0316.2234.0359.8467.44
2024.12
55.5------------
2025.06
54.663.5740.8756.9962.0348.0445.9150.4242.6818.9240.2859.0270.43
2024.12
53.2------------
2024.12
51.5------------
2024.12
49.3------------
2024.12
49------------
2024.12
48------------
2024.12
42.7------------
2024.12
36.7------------
2024.12
27.7------------
2024.12
25.6------------