| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Cell-Level Visual Question Answering | PBSBench Out of Domain | Accuracy (T/F)97 | 17 | |
| Cell-Level Visual Question Answering | PBSBench (In-domain) | True/False Accuracy77 | 17 | |
| Open-ended Question Answering | PBSBench Slide-level 1.0 (test) | BLEU-136 | 6 | |
| Fill-in-the-blank Question Answering | PBSBench Slide-level 1.0 (test) | Exact Match (EMatch)27 | 6 | |
| Multiple Choice Question Answering | PBSBench Slide-level 1.0 (test) | Accuracy85 | 6 | |
| True/False Question Answering | PBSBench Slide-level 1.0 (test) | Accuracy86 | 6 |