| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Navigation Visual Question Answering | NaVQA Short (S) horizon | Descriptive Accuracy76.2 | 23 | |
| Navigation Visual Question Answering | NaVQA Medium (M) horizon | Descriptive Accuracy73.7 | 7 | |
| Navigation Visual Question Answering | NaVQA | Positional Accuracy29.17 | 6 | |
| Embodied Question Answering | NaVQA | Response Latency (s)9.97 | 6 | |
| Descriptive Question Answering | NaVQA | Descriptive Question Accuracy67.2 | 6 | |
| Textual | NaVQA Long memory horizon | SR80 | 3 | |
| Textual | NaVQA Medium memory horizon | SR84 | 3 | |
| Textual | NaVQA Short memory horizon | SR82 | 3 | |
| Temporal | NaVQA Long memory horizon | SR88 | 3 | |
| Temporal | NaVQA Medium memory horizon | SR83 | 3 | |
| Temporal | NaVQA Short memory horizon | SR100 | 3 | |
| Spatial | NaVQA Long memory horizon | SR77 | 3 | |
| Spatial | NaVQA Medium memory horizon | SR84 | 3 | |
| Spatial | NaVQA Short memory horizon | SR89 | 3 | |
| Navigation Visual Question Answering | NaVQA Long (L) horizon | Descriptive Accuracy80 | 2 |