Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Helpfulness Assessment on Qualitative Assessment Dataset
Loading...
100
Not Overrefuse Rate (Content-safety)
EXAONE 3.5 32B
77.848
83.599
89.35
95.101
Sep 24, 2025
Not Overrefuse Rate (Content-safety)
Not Overrefuse Rate (Socio-economical)
Not Overrefuse Rate (Legal and Rights)
Not Overrefuse Rate (Overall)
Updated 27d ago
Evaluation Results
Method
Method
Links
Not Overrefuse Rate (Content-safety)
Not Overrefuse Rate (Socio-economical)
Not Overrefuse Rate (Legal and Rights)
Not Overrefuse Rate (Overall)
EXAONE 3.5 32B
Model Version=3.5, Par...
2025.09
100
100
100
100
EXAONE 3.5 7.8B
Model Version=3.5, Par...
2025.09
100
100
100
100
Llama-3.1-8B
Model Version=3.1, Par...
2025.09
100
100
100
100
Mi:dm 2.0-Base
Model Version=2.0-Base
2025.09
78.7
100
90.9
86.9
Feedback
Search any
task
Search any
task