Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Safety and Informativeness Evaluation on HarmfulQA Mathematics and Logic
Loading...
76.7
Safety Score
Qwen MoE-XL
52.364
58.682
65
71.318
May 30, 2026
Safety Score
Informativeness Score
Updated 1d ago
Evaluation Results
Method
Method
Links
Safety Score
Informativeness Score
Qwen MoE-XL
Base Model=Qwen-3B
2026.05
76.7
6.78
Mistral MoE-XL
Base Model=Mistral-7B
2026.05
65
7.9
Mistral
Base Model=Mistral-7B
2026.05
59.1
3.61
Qwen-3B
Base Model=Qwen-3B
2026.05
53.3
5.21
Feedback
Search any
task
Search any
task