Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Target behavior attack on HumanEval
Loading...
98.3
ASR
AiTM
-3.932
22.609
49.15
75.691
Feb 20, 2025
ASR
Updated 4d ago
Evaluation Results
Method
Method
Links
ASR
AiTM
Framework=MetaGPT, Vic...
2025.02
98.3
AiTM
Framework=Camel, Commu...
2025.02
97.6
AiTM
Framework=MetaGPT, Vic...
2025.02
97.6
AiTM
Framework=AutoGen, Com...
2025.02
96.3
AiTM
Framework=Camel, Commu...
2025.02
96.2
AiTM
Framework=AutoGen, Com...
2025.02
95.2
AiTM
Framework=Camel, Commu...
2025.02
94.7
AiTM
Framework=AutoGen, Com...
2025.02
90.4
AiTM
Framework=MetaGPT, Vic...
2025.02
90.4
AiTM
Framework=AutoGen, Com...
2025.02
82.6
AiTM
Framework=Camel, Commu...
2025.02
76.5
AiTM
Framework=MetaGPT, Vic...
2025.02
75.7
AiTM
Framework=ChatDev, Vic...
2025.02
60.1
AiTM
Framework=ChatDev, Vic...
2025.02
52.7
AiTM
Framework=ChatDev, Vic...
2025.02
0
AiTM
Framework=ChatDev, Vic...
2025.02
0
Feedback
Search any
task
Search any
task