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

Code Generation on HumanEval Python

75.6Pass@1

INTERVENOR

12.78429.09245.461.708Nov 16, 2023Apr 9, 2024Sep 1, 2024Jan 25, 2025Jun 19, 2025Nov 11, 2025Apr 6, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2023.11
75.6
74.4
2023.11
73.8
2023.11
71.9
2023.11
67
2023.11
62.2
61.6
2023.11
60.3
57.3
2023.11
47.6
2023.11
40.8
2026.04
40.1
2026.04
36.59
2023.11
35.9
35
2026.04
34.15
2023.11
30.9
2023.11
30.5
2023.11
22.9
2023.11
18.3
2023.11
15.2