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

Code Generation on MBPP (pass@1, Improvement Rate (%))

91.8Pass@1

AgentCoder

44.27256.61168.9581.289Dec 20, 2023May 7, 2024Sep 23, 2024Feb 9, 2025Jun 28, 2025Nov 14, 2025Apr 2, 2026
Updated 15d ago

Evaluation Results

MethodLinks
2023.12
91.834.4
2023.12
91.444.2
2023.12
89.972.2
2023.12
89.571.5
2023.12
87.728.4
2026.04
86.2-
2026.04
83.4-
2026.03
83.28-
2026.03
82.17-
2026.03
81.67-
2026.03
81.6-
2023.12
80.618
2026.03
80.3-
2026.03
80.2-
2026.03
80.1-
2026.03
80-
2023.12
79.812.9
2026.03
79.5-
2023.12
78.915.5
2023.12
78.9-
2026.03
78.9-
2023.12
78.7-
2026.03
78.6-
2026.03
78.46-
2025.12
78.3-
2026.03
77.43-
2026.03
77.3-
2026.03
77.3-
2023.12
77.112.9
2026.03
77.05-
2023.12
76.3183.6
2023.12
75.9135
2025.12
75.1-
2026.03
75.1-
2026.04
75-
2026.03
74.28-
2026.04
73.8-
2026.03
73.6-
2026.02
73.57-
2023.12
73.57.6
2025.12
73.5-
2026.03
73.19-
2025.12
72.5-
2023.12
72.4-
2026.03
72.36-
2026.03
72-
2026.03
71.95-
2026.03
71.83-
2026.03
71.83-
2023.12
71.436.8
2025.12
70.6-
2023.12
70.4-
2026.03
70.29-
2023.12
7034.1
2026.02
69.81-
2023.12
69.833.7
2026.04
69.6-
2023.12
69.3-
2025.12
69.3-
2023.12
69.2-
2025.12
69.2-
2023.12
68.4-
2023.12
68.3-
2023.12
68.230.7
2026.04
68.2-
2026.03
68.13-
2023.12
67.7-
2023.12
6728.4
2023.12
65.826.1
2023.12
65.826.1
2025.12
65.8-
2025.12
65.6-
2026.03
65.28-
2025.12
65.1-
2026.02
64.9-
2025.12
64-
2025.12
63.9-
2025.12
63.7-
2023.12
63.4-
2026.03
63-
2025.12
61.7-
2025.12
60.8-
2023.12
60.115.1
2026.03
60-
2026.03
60-
2025.12
58.7-
2023.12
58.612.3
2025.12
58.4-
2025.12
58.4-
2023.12
58.1-
2025.12
57.7-
2026.03
57-
2023.12
56.48
2025.12
56.1-
2026.03
56-
2026.02
54.12-
2026.02
53.23-
2023.12
52.2-
2026.02
50.58-
2023.12
46.1-11.7
Showing 100 of 159 rows