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

Code Generation on HumanEval+ (Pass@1, Avg, ΔScore)

88.3Pass@1

Uni-OPD

27.543243.316659.0974.8634Mar 13, 2026Mar 25, 2026Apr 7, 2026Apr 19, 2026May 2, 2026May 14, 2026May 27, 2026
Updated 6d ago

Evaluation Results

MethodLinks
2026.05
88.3--
2026.05
88--
2026.05
86.9--
2026.05
86.7--
2026.05
86.4--
2026.05
86.3--
2026.05
86.3--
2026.05
85.2--
2026.05
84.8--
2026.05
82.6--
2026.05
78.66--
2026.05
77.4--
2026.05
76.83--
2026.05
75.61--
2026.05
75--
2026.05
73.8--
2026.05
73.2--
2026.05
73.17--
2026.03
71.7979.120
2026.03
64.175.67-3.45
2026.05
64.02--
2026.05
61.59--
2026.03
61.5477.02-2.1
2026.05
60.37--
2026.03
53.8570.470
2026.05
52.4--
2026.05
50.61--
2026.05
50.6--
2026.05
49.4--
2026.03
43.5968.1-2.37
2026.03
38.4662.72-7.75
2026.05
32.93--
2026.05
31.1--
2026.05
29.88--
2026.05
-68.29-
2026.05
-87.2-
2026.05
-88.41-
2026.05
-0.61-
2026.05
-85.98-
2026.05
-86.59-