| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Question Answering | WebQA | ASR99.02 | 64 | |
| Multimodal Question Answering | WebQA Average | F1 Score50.8 | 32 | |
| Uncertainty Estimation | WebQA | AUROC73.57 | 30 | |
| Multimodal Question Answering | WebQA | F1-Recall90.92 | 22 | |
| Multi-modal Retrieval (Image Query) | WebQA | Recall@2043.55 | 21 | |
| Multi-modal Retrieval (Text Query) | WebQA | Recall@2076.52 | 21 | |
| Multi-modal retrieval (Text to Text/Image-Text) | WebQA | Recall@584.7 | 19 | |
| Multimodal Question Answering | WebQA Text-grounded n=2,455 (test) | F1 Score48.6 | 16 | |
| Multimodal Question Answering | WebQA Image-grounded n=2,511 (test) | F1 Score69.4 | 16 | |
| Multimodal Question Answering | WebQA Text | F1 Score54.9 | 16 | |
| Multimodal Question Answering | WebQA Image | F1 Score13.8 | 16 | |
| Poisoned Sample Detection | WebQA (IID) | Recall100 | 16 | |
| Poisoned sample detection | WebQA NIID-1 | Recall99.12 | 16 | |
| Watermark Detection | WebQA | Rank1.05 | 16 | |
| Image-based Question Answering | WebQA | Accuracy53.9 | 14 | |
| Narrative Reasoning | WebQA (test) | BLEURT0.623 | 14 | |
| Multimodal Retrieval-Augmented Generation | WebQA | ROrig59.3 | 12 | |
| Poisoned sample identification | WebQA | Recall100 | 12 | |
| Visual Question Answering | WebQA image segment 1.0 (test) | Accuracy49.8 | 12 | |
| Multimodal Question Answering | WebQA k=2 | ROrig@k64.8 | 8 | |
| Web-based Question Answering | WebQA (200 held-out questions) | Accuracy62.7 | 7 | |
| Multi-modal Retrieval (T->All) | WebQA+ | Recall@140.96 | 7 | |
| Open-domain Question Answering | WebQA CN | Accuracy57.15 | 6 | |
| Multimodal Question Answering | WebQA 3 (test) | Accuracy (%)79.5 | 6 | |
| Multimodal Retrieval | WebQA 2 | R@583.15 | 6 |