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

Code Generation on MBPP subset of 500 (test)

64.6Pass@1

Magicoder-S-DS

40.47246.7365359.264Dec 20, 2023
Updated 1mo ago

Evaluation Results

MethodLinks
2023.12
64.6
2023.12
64.4
2023.12
63.6
2023.12
62.8
2023.12
62.8
2023.12
60.6
2023.12
60.4
2023.12
52.2
2023.12
51.8
2023.12
51
2023.12
49.6
2023.12
49.4
2023.12
47.2
2023.12
47
2023.12
44.4
2023.12
43.5
2023.12
43.3
2023.12
41.4