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

Code Generation on HumanEval (pass@1, pass@5)

53.05Pass@1

CAA

20.75829.141537.52545.9085May 5, 2025May 30, 2025Jun 24, 2025Jul 20, 2025Aug 14, 2025Sep 8, 2025Oct 4, 2025
Updated 16d ago

Evaluation Results

MethodLinks
2025.10
53.0559.21
2025.10
52.1355.78
2025.10
52.1357.35
2025.10
48.1755.95
2025.05
43-
2025.05
36-
2025.05
36-
2025.10
35.7349.51
2025.05
34-
2025.05
33-
2025.10
27.4439.02
2025.05
22-