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

Coding on HumanEval (accuracy)

95.62Accuracy

DMoA

24.671243.090661.5179.9294Feb 27, 2026Mar 12, 2026Mar 25, 2026Apr 7, 2026Apr 20, 2026May 3, 2026May 17, 2026
Updated 14d ago

Evaluation Results

MethodLinks
2026.05
95.62
2026.05
91.22
2026.05
90.15
2026.05
89.4
2026.05
89.25
2026.05
89.02
2026.05
88.25
2026.05
87.14
2026.02
86.6
2026.05
85.7
2026.05
85.4
2026.05
85.24
2026.05
84.4
2026.05
84.25
2026.05
84.14
2026.05
84.1
2026.05
83.5
2026.05
82.48
2026.05
81.9
2026.02
81.7
2026.05
76.28
2026.05
75.82
2026.05
75.33
2026.05
74.05
2026.05
73.4
2026.05
73.28
2026.05
72
2026.05
70.4
2026.05
69.1
2026.05
68.8
2026.02
68.3
2026.05
68.3
2026.05
57.3
2026.05
57.3
2026.05
57.1
2026.05
54.9
2026.05
54.3
2026.05
54.3
2026.05
52.4
2026.05
50.7
2026.05
49.4
2026.02
48.2
2026.02
48.2
2026.03
44.5
2026.03
44.5
2026.03
41.5
2026.03
40.2
2026.03
40.2
2026.03
39.6
2026.03
37.8
2026.03
37.8
2026.03
37.8
2026.03
37.8
2026.02
36.6
2026.03
35.3
2026.03
32.9
2026.03
32.3
2026.03
32.3
2026.03
31.1
2026.03
27.4