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

Code Generation on HumanEval (Pass@1, 10, 100)

90.9Pass@1

Teacher

-0.6223.1446.970.66Feb 18, 2025Mar 29, 2025May 8, 2025Jun 16, 2025Jul 26, 2025Sep 3, 2025Oct 13, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.10
90.9--
2025.10
73.2--
2025.10
72--
2025.10
70.7--
2025.02
14.427.648.2
2025.02
12.925.244.5
2025.02
11.822.938.3
2025.02
10.521.235.6
2025.02
9.518.533.9
2025.02
8.917.828.4
2025.02
8.716.831.2
2025.02
7.815.119
2025.02
6.311.423.8
2025.02
6.213.720.5
2025.02
3.46.210.4
2025.02
3.15.814.2
2025.02
35.98.7
2025.02
2.95.111.8