OOD Detection
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
OOD Detection Source LLM GPT-4o (test)
98.7XSUM Score
19
OOD Detection Source LLM: Claude-3.5-Haiku (test)
0.977XSUM
19
OOD Detection Source LLM: Gemini-2.5-Flash (test)
96XSUM Score
19