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

Coding Tasks on MBPP+ instruct latest (test)

75.4Accuracy

FP16

21.94435.82249.763.578Dec 3, 2025
Updated 3mo ago

Evaluation Results

MethodLinks
2025.12
75.4
2025.12
64.8
2025.12
54.2
2025.12
42.3
2025.12
33.8
2025.12
24