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

Code Generation on HumanEval+ (Pass@1)

86Pass@1

Qwen2.5-Coder-7B-Inst

30.77645.11359.4573.787Oct 29, 2025Dec 5, 2025Jan 11, 2026Feb 18, 2026Mar 27, 2026May 3, 2026Jun 10, 2026
Updated 22d ago

Evaluation Results

MethodLinks
2026.04
86
2026.06
83.1
2026.06
82.93
2026.06
82.9
2026.06
82.9
2026.06
81.7
2026.06
81.55
2026.06
81.3
2026.06
81.29
2026.06
81.1
2026.06
81.1
2026.06
80.76
2026.06
80.61
2026.06
80.5
2026.06
80.3
2026.06
80.22
2026.06
79.9
2026.06
79.85
2026.06
79.3
2026.06
79.3
2026.06
79.15
2026.06
78.66
2026.06
78.66
2026.06
78.58
2026.06
78.35
2026.06
77.44
2026.06
76.83
2026.06
76.8
2026.06
76.8
2026.06
75.6
2025.10
75.3
2026.06
75
2026.06
75
2026.06
73.78
2026.06
73.17
2026.06
71.34
2026.06
70.73
2025.10
70.7
2025.10
70.7
2025.10
70.7
2025.10
70.6
2026.06
70.12
2026.06
70.12
2026.06
70.12
2026.06
68.29
2026.06
68.29
2025.10
67.4
2026.05
66
2026.06
65.85
2026.04
64
2026.04
64
2026.04
64
2026.04
62.8
2026.04
62.8
2025.10
62.2
2025.10
62.2
2026.04
61.6
2026.04
61
2026.05
61
2026.06
60.98
2026.06
60.37
2026.05
59.8
2025.10
59.8
2026.05
58.5
2026.05
56.1
2026.05
56
2026.05
53
2026.05
50
2026.05
50
2026.05
50
2026.05
46.3
2025.10
46.3
2026.05
42.7
2026.05
42.7
2026.05
42.1
2026.05
42.1
2026.05
41.5
2026.05
41.5
2026.05
40.2
2026.05
39.6
2026.05
39.6
2026.05
39.2
2026.05
39
2026.05
38.6
2026.05
38.4
2026.05
38.4
2026.05
38.4
2026.05
37.8
2026.05
37.8
2026.05
37.2
2025.10
37.2
2026.05
36.6
2026.05
36
2026.05
35
2026.05
34.6
2026.05
34.2
2026.05
33.8
2026.05
32.9
2026.05
32.9
2026.05
32.9
Showing 100 of 122 rows