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

Code Generation on EvalPlus (test)

86.7Eval+

Full

-3.46819.94143.3566.759Mar 19, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.03
86.7
2026.03
73.4
2026.03
68.7
2026.03
66.2
2026.03
34.1
2026.03
25.8
2026.03
25.6
2026.03
25.4
2026.03
25.4
2026.03
24.3
2026.03
22
2026.03
20.8
2026.03
11.2
2026.03
2.6
2026.03
2.4
2026.03
1.4
2026.03
0.9
2026.03
0.7
2026.03
0.3
2026.03
0
2026.03
0
2026.03
0
2026.03
0