Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Bias Detection on Toxigen (test)
Loading...
90.3
Accuracy
Toxigen
47.66
58.73
69.8
80.87
Apr 30, 2025
Accuracy
OF
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
OF
Toxigen
Model Category=Bias Cl...
2025.04
90.3
0.25
BiasGuard
2025.04
73.15
8
DeepSeek-R1-32B
Model Category=Rule-ba...
2025.04
70.83
13.5
DeepSeek-R1-32B
Model Category=LLMs as...
2025.04
70.3
8.85
GPT-4o
Model Category=Rule-ba...
2025.04
68.35
8.45
GPT-4o
Model Category=LLMs as...
2025.04
66.75
10.25
Llama-3-8B-it
Model Category=Rule-ba...
2025.04
63.3
12.45
Moderation API
Model Category=Bias Cl...
2025.04
60.85
0.1
Azure API
Model Category=Bias Cl...
2025.04
57.08
7.94
ShieldGemma
Model Category=Bias Cl...
2025.04
56.2
0.3
Llama-3-8B-it
Model Category=LLMs as...
2025.04
50.2
24.4
Llama-Guard-3
Model Category=Bias Cl...
2025.04
49.3
9.4
Feedback
Search any
task
Search any
task