Hallucination Detection on HaluBench
73.89Unsafe F1 ScoreGPT-4o
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-4o2026.05 | 73.89 | |
| best pooling2026.05 | 48.63 | |
| SURE-RAG2026.05 | 33.43 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| GPT-4o2026.05 | 73.89 | |
| best pooling2026.05 | 48.63 | |
| SURE-RAG2026.05 | 33.43 |