| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Assessment | MHumanEval | Response Rate72.6 | 20 | |
| Code Generation | mHumanEval | Pass@10.94 | 13 | |
| Object Hallucination Evaluation | MHumanEval | Hallucination Rate (%)56 | 12 | |
| Multi-type Hallucination Evaluation | MHumanEval | Object Hallucination Rate21.9 | 9 |