| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMAU | Accuracy81.1 | 57 | 25d ago | ||
| MMAU v05.15.25 (test-mini) | Step-Audio 2 | Sound Score84.04 | 54 | 2mo ago | |
| MMAU v05.15.25 (test) | Step-Audio 2 | Sound Score84.04 | 53 | 4mo ago | |
| AudioMarathon | FastV | SER16.8 | 48 | 2mo ago | |
| MMAU Pro | Average Score100 | 42 | 1mo ago | ||
| MMSU | UAS-Audio | Perception Score55.7 | 37 | 1mo ago | |
| MMAU (test) | Speech Score76.58 | 31 | 1mo ago | ||
| MMAR (comprehensive evaluation) | MPAR2 | Sound Score62.4 | 25 | 3mo ago | |
| X-Ares | SPEAR-XLarge | ASV201599.81 | 21 | 4mo ago | |
| MMAU mini original (test) | MiMo-Audio | Accuracy (Sound Domain)80.78 | 21 | 4mo ago | |
| MMAU mini (test) | Audio-DeepThinker | Accuracy78.5 | 20 | 3mo ago | |
| MMAR (test) | Qwen3-Omni-Instruct | Performance67.1 | 20 | 4mo ago | |
| ClothoAQA | Qwen2.5-Omni-7B + CoAT | Accuracy87.17 | 20 | 1mo ago | |
| MMAU audio | MiniCPM-O 2.6 + MoD-DPO | Sound Score72.08 | 19 | 1mo ago | |
| MMAR | Average Score83.7 | 15 | 3mo ago | ||
| MMSU (test) | Covo-Audio | Overall Score66.64 | 15 | 4mo ago | |
| MMAU | Overall Score80.4 | 14 | 1mo ago | ||
| TUT 2017 | ERNIE 5.0 | Accuracy68.09 | 14 | 3mo ago | |
| Audio Understanding Evaluation Suite LS100h CD FSC LibCnt LSMF RAV VocS FMA GTZAN MT NSynth Clo DES ESC Urb8 | Ming-UniAudio | LS100h Score93.45 | 13 | 1mo ago | |
| XARES-LLM Track B | Track B Score68.5 | 12 | 1mo ago | ||
| LLaSO-Eval | FlexiSLM-7B | Accuracy (CremaD Emotion)50 | 11 | 24d ago | |
| AudioCaps | Qwen2.5-Omni-3B | LB Score42.82 | 11 | 2mo ago | |
| MMAU Text instruction | Audio Flamingo 2 | Sound Score71.47 | 9 | 1mo ago | |
| MMAU v05.15.25 | Step Audio2 Mini | Sound Score79.3 | 9 | 3mo ago | |
| MMAU Pro (test) | Performance59.2 | 8 | 4mo ago |