| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Differential Diagnosis | Our Benchmark | Diagnostic Accuracy45.26 | 14 | |
| Image Description | Our Benchmark | METEOR23.64 | 14 | |
| AI-generated image detection | Our benchmark In-the-Wild | Accuracy96.7 | 5 | |
| AI-generated image detection | Our benchmark In-the-Lab | Accuracy97.4 | 5 | |
| AI-generated image detection | Our benchmark (Overall) | Accuracy97.05 | 5 | |
| Indirect injection interception | Our Benchmark indirect EN n=180 | IR95.6 | 2 |