List your company

Bias Detection on Toxigen (test)

90.3AccuracyToxigen
47.6658.7369.880.87Apr 30, 2025

Evaluation results

MethodLinks
ToxigenModel Category=Bias Classifier2025.0490.30.25
BiasGuard2025.0473.158
DeepSeek-R1-32BModel Category=Rule-based LLMs as Judges2025.0470.8313.5
DeepSeek-R1-32BModel Category=LLMs as Judges2025.0470.38.85
GPT-4oModel Category=Rule-based LLMs as Judges2025.0468.358.45
GPT-4oModel Category=LLMs as Judges2025.0466.7510.25
Llama-3-8B-itModel Category=Rule-based LLMs as Judges2025.0463.312.45
Moderation APIModel Category=Bias Classifier2025.0460.850.1
Azure APIModel Category=Bias Classifier2025.0457.087.94
ShieldGemmaModel Category=Bias Classifier2025.0456.20.3
Llama-3-8B-itModel Category=LLMs as Judges2025.0450.224.4
Llama-Guard-3Model Category=Bias Classifier2025.0449.39.4