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

Prompt Injection on CSQA

18.33ASR@3

G-Safeguard

17.0525.6934.3342.97Aug 11, 2025Sep 2, 2025Sep 24, 2025Oct 16, 2025Nov 7, 2025Nov 29, 2025Dec 21, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
18.33100
2025.12
18.33100
2025.12
18.6798.22
2025.08
18.6799.56
2025.08
1999.11
2025.08
19.33100
2025.08
19.33100
2025.12
19.67100
2025.12
20.6791.11
2025.12
21.6787.11
2025.08
2285.78
2025.12
22.6689.78
2025.08
22.6750.67
2025.12
23.3383.56
2025.12
23.6777.78
2025.12
23.6755.56
2025.08
23.6780
2025.08
2474.67
2025.12
2554.22
2025.12
2575.11
2025.12
2575.11
2025.12
2590.67
2025.12
25.6746.67
2025.08
2653.78
2025.12
26.3344.89
2025.12
26.3352
2025.08
2744.89
2025.08
27.3355.11
2025.12
2854.67
2025.08
28.6757.33
2025.08
29.3350.67
2025.08
3075.11
2025.12
30.3350.67
2025.08
30.3347.11
2025.12
31.3353.78
2025.12
31.3344.44
2025.12
32.67-
2025.08
33-
2025.12
3445.33
2025.12
34.3356.44
2025.08
34.3356.89
2025.08
34.6752.44
2025.08
35.3345.33
2025.08
3746.67
2025.12
38-
2025.08
38.6738.22
2025.12
40.3344
2025.08
42-
2025.08
42.33-
2025.12
43-
2025.12
47-
2025.08
50.33-