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

Coding on MBPP (Accuracy)

98.4Accuracy

GPT-5

33.202450.128767.05583.9813Jan 7, 2026Jan 11, 2026Jan 16, 2026Jan 20, 2026Jan 25, 2026Jan 29, 2026Feb 3, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.01
98.4
2026.01
83.7
2026.01
83.6
2026.01
83.6
2026.01
82.6
2026.01
81.8
2026.01
79
2026.01
78.7
2026.01
77.7
2026.01
75.9
2026.01
75.4
2026.01
72.22
2026.01
72.1
2026.01
70.37
2026.01
68.78
2026.01
68.7
2026.01
68.4
2026.01
67.7
2026.01
64.7
2026.01
64.2
2026.02
59.3
2026.01
57.7
2026.02
55.3
2026.01
53.97
2026.02
52.8
2026.01
52.6
2026.02
51.9
2026.02
51.6
2026.02
51
2026.01
42.59
2026.01
35.71