Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Red Teaming Evaluation on CAGE 200 episodes 4
Loading...
3.74
AHD
Qwen3-0.6B
3.4828
5.2189
6.955
8.6911
May 16, 2026
AHD
ECR
AAC
Updated 2mo ago
Evaluation Results
Method
Method
Links
AHD
ECR
AAC
Qwen3-0.6B
Category=General-purpose
2026.05
3.74
7
2,490
QwQ-32B
Category=Reasoning-spe...
2026.05
6.67
60
266
DeepHat-7B
Category=Domain-specia...
2026.05
10.01
8
9,741
Qwen3-1.7B
Category=General-purpose
2026.05
10.09
2
1,103
Foundation-Sec-8B
Category=Domain-specia...
2026.05
10.13
13
21,746
DeepSeek-R1-14B
Category=Reasoning-spe...
2026.05
10.17
26
290
Feedback
Search any
task
Search any
task