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

Code Debugging on MBPP

80.8Accuracy

MGDebugger

64.78468.94273.177.258Oct 2, 2024
Updated 3mo ago

Evaluation Results

MethodLinks
2024.10
80.841.1
2024.10
8039
2024.10
78.634.4
2024.10
77.430.7
2024.10
76.828.8
2024.10
76.832.9
2024.10
76.628.7
2024.10
76.431.8
2024.10
75.830
2024.10
75.228.3
2024.10
7523.3
2024.10
7420.7
2024.10
7420.2
2024.10
73.623.7
2024.10
73.418.9
2024.10
72.816.6
2024.10
72.816.6
2024.10
72.616.5
2024.10
72.616.5
2024.10
72.616
2024.10
72.219.7
2024.10
7219.1
2024.10
71.814
2024.10
71.818.5
2024.10
71.617.9
2024.10
71.212.2
2024.10
69.46.7
2024.10
67.4-
2024.10
67.2-
2024.10
65.4-