| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Long-Form Speech Understanding | AudioMarathon 1.0 (test) | Average Score65.6 | 16 | |
| Audio Classification | AudioMarathon 1.0 (test) | SED Score78.4 | 15 | |
| Speaker Information Modeling | AudioMarathon 1.0 (test) | SD (Score)72.3 | 15 | |
| Speech Content Extraction | AudioMarathon 1.0 (test) | SER12.4 | 15 | |
| Sound Event Detection | AudioMarathon | SED F178.4 | 11 |