OpenAI APIs
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
OpenAI APIs Freeform Malicious
84F1 Score
2
OpenAI APIs Freeform Benign
63.94F1
2
OpenAI APIs FourOptions Malicious
78.33F1 Score
2
OpenAI APIs FourOptions Benign
80.59F1 Score
2
OpenAI APIs TwoOptions Malicious
84.44F1 Score
2
OpenAI APIs TwoOptions Benign
79.81F1 Score
2