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

Helpfulness Evaluation on Alpaca Eval

90Alpaca Eval (%)

No Defense

-2.5621.4745.569.53May 31, 2025Jul 2, 2025Aug 3, 2025Sep 5, 2025Oct 7, 2025Nov 8, 2025Dec 11, 2025
Updated 18d ago

Evaluation Results

MethodLinks
2025.08
90
2025.08
90
2025.08
90
2025.08
88
2025.08
88
2025.08
62
2025.08
60
2025.08
59
2025.08
57
2025.08
56
2025.08
56
2025.08
55
2025.08
52
2025.08
51
2025.08
50
2025.08
33
2025.08
21
2025.05
17.77
17.59
2025.05
16.88
2025.12
16.33
2025.05
16.21
16.05
15.51
2025.12
14.71
2025.12
13.15
2025.05
13.04
12.28
12.21
2025.05
11.78
2025.05
11.32
2025.12
10.99
9.93
8.64
8.64
2025.12
7.34
2025.05
6.9
6.66
6.66
2025.08
5
2025.08
4
2025.08
1