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

Code Generation on HumanEval (Acc, AMSR)

98.2Accuracy (HumanEval)

Dense

74.69680.79886.993.002Jul 29, 2025
Updated 19d ago

Evaluation Results

MethodLinks
2025.07
98.20
2025.07
97.222.1
2025.07
96.921.5
2025.07
96.80
2025.07
94.516.8
2025.07
93.30
2025.07
91.520.8
2025.07
88.420.1
2025.07
87.29.6
2025.07
86.620.4
2025.07
85.415.3
2025.07
81.214.8
2025.07
79.921.7
2025.07
79.311.5
2025.07
75.66.2