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

Code Generation on MBPP (MBPP Pass@1)

65.1MBPP Pass@1

Trajectory Replay

29.42838.68947.9557.211Jan 22, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.01
65.1
2026.01
65
2026.01
62.1
2026.01
62.1
2026.01
62
2026.01
61.8
2026.01
58.4
2026.01
58.4
2026.01
58.3
2026.01
58.1
2026.01
55.2
2026.01
55
2026.01
48
2026.01
47.9
2026.01
31
2026.01
30.8