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

Code Generation on MBPP OOD Generalization (trained on CodeContests)

85.45Pass@128

Base (No-train)

73.614876.687479.7682.8326Mar 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.03
85.45
2026.03
85.45
2026.03
85.13
2026.03
83.33
2026.03
81.22
2026.03
81.22
2026.03
79.63
2026.03
78.31
2026.03
74.07