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

Code Generation on MBPP (accuracy (%))

92.2Accuracy (%)

MegaAgent

35.41650.15864.979.642Aug 19, 2024Nov 18, 2024Feb 17, 2025May 19, 2025Aug 18, 2025Nov 17, 2025Feb 17, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2024.08
92.2
2025.06
88.6
2025.06
86.9
2025.06
86.5
2025.06
86.5
2025.06
85.4
2024.08
85.3
2025.06
84.7
2025.12
83.27
2024.08
82.4
2024.08
81.7
2025.12
80.16
2025.12
79.77
2025.12
79.4
2025.12
78.21
2024.08
78.1
2026.01
77.49
2025.12
77.43
2025.12
77.1
2025.12
77.04
2026.01
76.7
2025.12
76.6
2025.12
76
2026.01
75.45
2025.12
75
2025.12
74.6
2026.02
73.8
2026.01
73.27
2025.12
68.2
2025.12
67.45
2026.01
66.93
2025.12
65.4
2026.01
65.37
2026.02
65
2026.02
64.6
2026.02
63.2
2026.02
62.8
2026.02
62.4
2025.12
62.26
2025.12
61.87
2026.02
61.3
2026.02
61.3
2026.02
60.2
2026.02
59.9
2026.02
57.8
2026.02
56.8
2026.02
56.5
2025.12
56.2
2026.02
55.8
2026.02
55.8
2025.12
55.8
2025.05
55.76
2026.02
55.6
2026.02
55.4
2026.02
55.2
2026.02
54.8
2026.02
54.4
2025.05
54.32
2026.02
53.48
2026.02
52.6
2025.12
52.4
2025.05
52.16
2025.05
52.16
2026.01
51.36
2026.01
50.58
2025.05
50
2025.05
49.9
2026.01
49.81
2026.02
49.7
2025.05
48.56
2026.02
48.4
2026.01
47.86
2026.02
47.2
2026.02
46.4
2025.12
46.2
2025.12
46
2026.02
45
2026.02
44.8
2025.05
44.6
2026.02
43.7
2026.01
43.19
2025.12
43
2026.01
42.02
2026.01
42.02
2026.01
41.25
2026.02
41
2026.02
40.4
2026.02
40
2026.02
39.8
2026.02
39.8
2026.02
39.8
2026.02
39.6
2026.01
39.6
2026.02
39.4
2025.12
39.2
2026.01
38.4
2025.12
38.2
2026.02
38
2026.02
38
2026.02
37.6
Showing 100 of 146 rows