Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Python Coding on MBPP standard (test)

85.25Pass@1 Accuracy

CoT

-3.4119.607542.62565.6425Sep 11, 2023Feb 7, 2024Jul 5, 2024Dec 1, 2024Apr 29, 2025Sep 25, 2025Feb 21, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
85.25
2026.02
79.39
2026.02
74.94
2026.02
73.07
2026.02
69.79
2026.02
67.92
2026.02
66.51
2024.03
65.8
2026.02
64.64
2024.03
63.4
2024.03
59.5
2024.03
54.9
2024.03
52.5
2024.03
47.5
2023.09
43.5
2024.03
40.9
2023.09
37.7
2023.09
37.7
2024.03
37.7
2024.03
33.9
2024.03
30.4
2024.03
29.2
2023.09
27.3
2024.03
23.7
2023.09
22.6
2023.09
20.8
2024.03
19.8
2023.09
17.7
2023.09
11.7
2023.09
0
2023.09
0
2023.09
0