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

Coding on MBPP (Solve Rate)

83.28Solve Rate

CapFlow

30.988844.564458.1471.7156Feb 11, 2026Feb 16, 2026Feb 22, 2026Feb 27, 2026Mar 5, 2026Mar 10, 2026Mar 16, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
83.28-
2026.02
82.99-
2026.02
82.69-
2026.02
82.11-
2026.02
81.23-
2026.02
72.72-
2026.02
72.72-
2026.02
70.96-
2026.02
70.67-
2026.02
70.08-
2026.02
69.5-
2026.03
39.6-
2026.03
35.6-
2026.03
35.2-
2026.03
33-