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

Coding on MBPP (pass@1 accuracy)

95.33Pass@1 Accuracy

SwiR

20.418839.866959.31578.7631Oct 6, 2025Nov 4, 2025Dec 3, 2025Jan 2, 2026Jan 31, 2026Mar 1, 2026Mar 31, 2026
Updated 17d ago

Evaluation Results

MethodLinks
2025.10
95.33
2025.10
94.16
2025.10
94.16
2026.03
93.3
2025.10
91.44
2026.03
90
2026.03
86.7
2026.03
86.7
2026.03
86.7
2026.03
83.3
2026.03
83.3
2026.03
80
2026.03
80
2026.03
80
2026.03
79.5
2026.03
76.8
2026.03
75.1
2026.03
73.3
2026.03
72.5
2026.03
68.5
2026.03
66.7
2026.03
50.6
2026.03
49.8
2026.03
46.7
2026.03
45.6
2026.03
43.3
2026.03
40
2026.03
33.3
2026.03
26.7
2026.03
23.3