Harmful Query Evaluation Set
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
Harmful Query Evaluation Set Claude Haiku 4.5 N=750
1.01Toxicity
10
N=750 Harmful Query Evaluation Set Gemini-3.1-Flash-Lite
2.75Toxicity
10
Harmful Query Evaluation Set Gemini-2.5-Flash N=750
2.18Toxicity
10
Harmful Query Evaluation Set GPT-5.4-mini N=750
1.01Toxicity Score
10
Harmful Query Evaluation Set N=750 GPT-5.4-nano
1.05Toxicity Score
10