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

Utility Prediction Routing on MathVista

89.3OpenAI Score

Oracle

20.753638.549356.34574.1407May 19, 2025
Updated 16d ago

Evaluation Results

MethodLinks
2025.05
89.363.66
2025.05
72.9650.29
2025.05
71.5450.97
2025.05
70.8550.28
2025.05
70.8548.22
2025.05
70.1250.97
2025.05
67.2748.87
2025.05
66.5746.1
2025.05
65.8849.57
2025.05
64.4844.71
2025.05
64.4648.2
2025.05
64.4549.61
2025.05
60.248.89
2025.05
52.9136.96
2025.05
42.4632.82
2025.05
41.6133.87
2025.05
39.128.21
2025.05
34.4824.69
2025.05
33.6333.06
2025.05
32.630.24
2025.05
32.1124.7
2025.05
30.4229.75
2025.05
29.7248.46
2025.05
23.3924.23
2025.05
23.3924.92
2025.05
23.3933.07