| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMAU v05.15.25 (test) | Step-Audio 2 | Sound Score84.04 | 28 | 4d ago | |
| MMAU v05.15.25 (test-mini) | Step-Audio 2 | Sound Score84.04 | 28 | 4d ago | |
| MMAU (test) | Speech Score76.58 | 25 | 4d ago | ||
| MMAR (test) | Qwen3-Omni-Instruct | Performance67.1 | 20 | 4d ago | |
| MMAU | Accuracy80.8 | 20 | 4d ago | ||
| MMAR (comprehensive evaluation) | Gemini 2.0 Flash | Sound Score61.21 | 15 | 4d ago | |
| MMSU (test) | Covo-Audio | Overall Score66.64 | 15 | 4d ago | |
| MMAR | Gemini-2.5-Pro | MMAR74.7 | 12 | 4d ago | |
| MMAU Pro (test) | Performance59.2 | 8 | 4d ago | ||
| ClothoAQA | Qwen3-Omni-Instruct | Accuracy75.16 | 7 | 4d ago | |
| TUT 2017 | ERNIE 5.0 | Accuracy68.09 | 7 | 4d ago | |
| Clotho V2 | Uni-MoE w/ MoE-Task3 | CIDEr25.1 | 6 | 2d ago | |
| ClothoAQA | Uni-MoE w/ MoE-Task3 | CIDEr32.6 | 6 | 2d ago | |
| Clotho V1 | Uni-MoE w/ MoE-Task3 | CIDEr25 | 5 | 2d ago | |
| Dynamic-Superb (test) | UniAudio 1.5 | Accent Classification Accuracy24 | 4 | 4d ago | |
| MMAU Mini | Bagpiper | MMAU-Mini Score0.745 | 3 | 4d ago | |
| Clotho V2 (test) | - | CIDEr- | 0 | 4d ago | |
| Clotho V1 (test) | - | CIDEr- | 0 | 4d ago | |
| ClothoAQA (held-out test) | - | CIDEr- | 0 | 4d ago |