| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Text-to-Image Factuality Evaluation | I-HallA History | FAGER87.76 | 6 | |
| Text-to-Image Factuality Evaluation | I-HallA Science 99 | FAGER Score90.83 | 6 | |
| Factual A/B test | I-HallA History 99 pairs (test) | Pairwise Accuracy83 | 3 |