| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MMAR | AUDIO-MIND | Average Score80.4 | 55 | 1mo ago | |
| MUSIC-AVQA 1.0 (test) | QA-TIGER | Counting Accuracy84.86 | 43 | 4mo ago | |
| MMSU | Gemini 2.5 Pro (May 25) | Score77.7 | 31 | 1mo ago | |
| MMAU | Score77.5 | 28 | 2mo ago | ||
| MUSIC-AVQA (test) | InternVideo2_S2 | Accuracy (Avg)80.51 | 17 | 4mo ago | |
| ClothoAQA (test) | VideoLLaMA2.1-AV | Accuracy71.02 | 14 | 4mo ago | |
| OpenBookQA | Qwen3-Omni-Flash-Instruct | Score91.4 | 12 | 4mo ago | |
| SD-QA | Qwen3-Omni-Flash-Instruct | Score76.8 | 12 | 4mo ago | |
| CommonEval | Qwen3-Omni-Flash-Instruct | Score91 | 12 | 4mo ago | |
| AlpacaEval | Ming-Flash-Omni | AlpacaEval AQA Score95.58 | 12 | 4mo ago | |
| WenetSpeech-QA | GLM-4-Voice | Audio-QA Score48.47 | 12 | 4mo ago | |
| Tripoli-QA | GLM-4-Voice | Audio QA Score44.99 | 12 | 4mo ago | |
| Listen, Quizzing (LQ.) | GLM-4-Voice | Audio-QA Score62.67 | 12 | 4mo ago | |
| AudioSet En | GLM-4-Voice | Audio QA Score44.87 | 12 | 4mo ago | |
| AudioCaps-QA (test) | M3KG-RAG | Model-as-Judge Score60.77 | 12 | 4mo ago | |
| Clotho (test) | GST-T2 | Token-Level Accuracy52.8 | 11 | 2mo ago | |
| ChimeHome (test) | Token-Level Accuracy96.7 | 11 | 2mo ago | ||
| AudioCaps (test) | Token-Level Accuracy60.1 | 11 | 2mo ago | ||
| speech-web-questions (S-Web) | Qwen3-Omni | Accuracy74.9 | 11 | 2mo ago | |
| RACE Audio | Uni-MoE w/ MoE-Task4 (4E) | Accuracy (Sub-task 1)64.21 | 10 | 4mo ago | |
| SH-Bench (test) | Step-Audio-2-mini + BPFT | Accuracy (Main Speaker, General)0.974 | 10 | 4mo ago | |
| MMAU-style Complex QA | Speech-Hands | Accuracy85.7 | 9 | 4mo ago | |
| Multi-sound-object soundscapes | Qwen2.5-Omni | Accuracy72.1 | 9 | 4mo ago | |
| Bio-acoustic QA | Speech-Hands | Accuracy81.25 | 9 | 4mo ago | |
| MMAU v05.15.25 (test) | AQA-TTRL | Accuracy0.7374 | 8 | 1mo ago |
