| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Hallucination Evaluation | MMHal-Bench | MMHal Score84.2 | 309 | |
| Multimodal Hallucination Evaluation | MMHal-Bench | Average Score46 | 140 | |
| Image+Text-to-Text Hallucination Evaluation | MMHal-Bench | BERT Score79 | 18 | |
| Vision-Language Hallucination | MMHal-Bench | Hal32 | 13 | |
| Generative Hallucination Mitigation | MMHal-Bench | Overall Score3.49 | 13 | |
| Multi-modal Hallucination Evaluation | MMHal-Bench v1.0 (test) | Overall Score2.14 | 12 | |
| Hallucination Evaluation | MMHal-Bench-V | Hallucination Score2.57 | 9 | |
| Multi-modal Hallucination Evaluation | MMHal-Bench | Attribute Failure Score1.83 | 5 |