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

Code Generation on MBPP+ (Accuracy & Improvement)

76.9Accuracy

Primitives-based MAS

38.21248.25658.368.344Feb 3, 2026Feb 10, 2026Feb 18, 2026Feb 25, 2026Mar 5, 2026Mar 12, 2026Mar 20, 2026
Updated 26d ago

Evaluation Results

MethodLinks
2026.02
76.98.4
2026.02
76.412.9
2026.02
75.77.2
2026.02
75.77.2
2026.02
74.66.1
2026.02
73.810.3
2026.02
73.85.3
2026.02
73.510
2026.02
72.84.3
2026.02
72.28.7
2026.02
72.28.7
2026.02
69.86.3
2026.02
68.5-
2026.03
67.9-
2026.03
67.5-
2026.03
66.4-
2026.03
66.40
2026.03
66.40
2026.03
66.1-
2026.03
65.9-
2026.03
65.08-
2026.03
64.81-
2026.02
63.5-
2026.03
63.5-
2026.03
54.2-
2026.03
51.615.9
2026.03
51.6-
2026.03
51.1-
2026.03
39.7-