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

Code Generation on MBPP

79.8Accuracy

GPT-4o

34.279246.097157.91569.7329Oct 10, 2023Mar 4, 2024Jul 28, 2024Dec 22, 2024May 17, 2025Oct 10, 2025Mar 6, 2026
Updated 1mo 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
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
2026.02
41.8
2025.06
41.6
2026.02
41.6
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
2025.06
37.2
2024.05
37.2
2025.06
36.85
2025.06
36.44
2025.06
36.16
2026.03
36.03
Showing 100 of 159 rows