Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Robustness Assessment on RAI Robustness Assessment
Loading...
43.7
Content-safety (ASR)
EXAONE 3.5 7.8B
30.284
33.767
37.25
40.733
Sep 24, 2025
Content-safety (ASR)
Socio-economical (ASR)
Legal and Rights (ASR)
Overall (ASR)
Updated 27d ago
Evaluation Results
Method
Method
Links
Content-safety (ASR)
Socio-economical (ASR)
Legal and Rights (ASR)
Overall (ASR)
EXAONE 3.5 7.8B
Model size=7.8B, Versi...
2025.09
43.7
59.9
52.5
49.2
Llama-3.1-8B
Model size=8B, Version...
2025.09
36.4
45.2
45.7
41.8
EXAONE 3.5 32B
Model size=32B, Versio...
2025.09
35.5
49.7
43.1
40.2
Mi:dm 2.0-Base
2025.09
30.8
46.9
40.8
36.7
Feedback
Search any
task
Search any
task