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

Code Generation on MBPP

79.8Accuracy

GPT-4o

35.70447.15258.670.048Oct 10, 2023Mar 17, 2024Aug 23, 2024Jan 29, 2025Jul 7, 2025Dec 13, 2025May 21, 2026
Updated 9d ago

Evaluation Results

MethodLinks
2025.12
79.8
2025.12
79.01
2026.02
78.9
2025.12
78.59
2025.12
78.34
2024.07
76.9
2026.03
75.15
2026.03
74.54
2026.03
74.2
2026.03
74.2
2024.07
73.4
2026.03
72.37
2024.07
71.9
2024.07
71.7
2026.03
71.4
2024.07
71.2
2024.07
70.9
2024.07
70.4
2025.12
69.1
2025.12
68.85
2026.03
68.6
2025.12
67.25
2025.10
67
2024.07
66.9
2025.12
66.25
2024.07
66.2
2025.10
65.8
2025.10
65.6
2024.07
65.5
2025.12
65.41
2026.03
64.4
2024.07
64.2
2024.07
63.9
2026.03
60.6
2026.03
59.14
2025.10
58.3
2025.10
57.8
2026.03
57.8
2025.10
56.4
2025.10
56.2
2025.02
55.1
2025.02
54.4
2023.10
52.5
2025.10
51.6
2025.02
50.9
2025.12
50.88
2025.02
49.9
2025.10
49.8
2025.02
49.6
2025.02
49.4
2025.02
48.4
2026.02
48.4
2025.10
48.4
2024.07
47.6
2023.10
47.5
2024.07
47.5
2024.10
47.2
2026.02
46.2
2026.02
45
2024.10
44.6
2024.07
44.4
2026.02
44.4
2026.05
44.4
2026.05
44
2026.05
43.6
2026.05
43.2
2025.10
43.1
2025.10
42.8
2026.02
42.4
2026.02
42.2
2026.02
42.1
2026.02
42.1
2024.10
42
2024.10
42
2026.05
41.9
2026.02
41.8
2025.06
41.6
2026.02
41.6
2026.05
41.1
2025.06
41.08
2026.02
41
2026.02
40.6
2026.02
40.6
2026.02
40.4
2025.06
39.92
2026.02
39.8
2025.06
39.72
2026.02
39.4
2026.02
39.4
2025.06
39.32
2025.06
39.04
2024.10
39.02
2025.06
39
2025.06
38.92
2025.06
38.8
2025.06
38.56
2026.02
38.4
2025.06
38.24
2025.02
38.1
2026.02
37.4
Showing 100 of 165 rows