| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Retrieval-Augmented Question Answering | DeepSearch Average | SR57.1 | 23 | |
| Retrieval-Augmented Question Answering | DeepSearch Bamboogle | Success Rate (SR)72 | 23 | |
| Retrieval-Augmented Question Answering | DeepSearch Musique | SR46 | 23 | |
| Retrieval-Augmented Question Answering | DeepSearch 2wiki | Success Rate (SR)68 | 23 | |
| Retrieval-Augmented Question Answering | DeepSearch HotpotQA | Success Rate56 | 23 | |
| Retrieval-Augmented Question Answering | DeepSearch PopQA | Success Rate64 | 23 | |
| Retrieval-Augmented Question Answering | DeepSearch TriviaQA | Success Rate (SR)78 | 23 | |
| Retrieval-Augmented Question Answering | DeepSearch NQ | SR86 | 23 | |
| Deep Research Task | DeepSearch | Accuracy (%)47 | 11 |