Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Malicious Code Generation on Malicious Code Generation Dataset (test)
Loading...
19.38
ASR (Claude3.5)
SPELL
-0.7752
4.4574
9.69
14.9226
Dec 24, 2025
ASR (Claude3.5)
ASR (GPT4.1)
ASR (Qwen2.5 Coder)
Overall ASR
Updated 5mo ago
Evaluation Results
Method
Method
Links
ASR (Claude3.5)
ASR (GPT4.1)
ASR (Qwen2.5 Coder)
Overall ASR
SPELL
2025.12
19.38
83.75
68.13
57.09
Redcode
2025.12
18.13
91.88
10.63
40.21
Random Selection
2025.12
16.88
53.13
60.63
43.54
CL-GSO
2025.12
7.5
5.63
5.63
6.25
RL-breaker
2025.12
0
0
27.5
8.33
DRA
2025.12
0
0
0
0
CodeAttack
2025.12
0
0
0
0
Feedback
Search any
task
Search any
task