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

Code Generation on HumanE

85.2Accuracy

Denser

67.5272.1176.781.29Dec 17, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
85.2
2025.12
84.8
2025.12
84.2
2025.12
83.6
2025.12
83.1
2025.12
83
2025.12
82.7
2025.12
82.4
2025.12
82.1
2025.12
81.7
2025.12
81.4
2025.12
80.9
2025.12
80.3
2025.12
79.7
2025.12
79.6
2025.12
79.1
2025.12
78.5
2025.12
77.9
2025.12
77.8
2025.12
77.3
2025.12
76.9
2025.12
76.8
2025.12
76.8
2025.12
76.3
2025.12
76.2
2025.12
76.1
2025.12
76
2025.12
75.7
2025.12
75.5
2025.12
75.4
2025.12
75.2
2025.12
74.8
2025.12
74.6
2025.12
74.6
2025.12
74.5
2025.12
74.2
2025.12
73.9
2025.12
73.8
2025.12
73.7
2025.12
73.6
2025.12
73.6
2025.12
73.4
2025.12
73.2
2025.12
72.9
2025.12
72.8
2025.12
72.7
2025.12
72.1
2025.12
72.1
2025.12
71.5
2025.12
71.3
2025.12
71.2
2025.12
71
2025.12
70.5
2025.12
70.4
2025.12
69.7
2025.12
68.2