| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MUSIC-AVQA 1.0 (test) | Sparsify | AV Localis Accuracy85.09 | 96 | 3mo ago | |
| AVQA | ContextGuard | Accuracy87.3 | 85 | 1d ago | |
| MUSIC-AVQA (test) | VAST | Acc (Avg)80.7 | 76 | 7d ago | |
| AVQA (test) | UniMVU | Total Accuracy94.3 | 36 | 7d ago | |
| Music-AVQA | VideoLLaMA2 | Accuracy81.3 | 33 | 3mo ago | |
| MUSIC-AVQA Bias v2.0 (test) | AV-Master | Total Accuracy78.39 | 28 | 1mo ago | |
| MUSIC-AVQA balanced v2.0 (test) | LAST-Att | Total Accuracy75.44 | 28 | 1mo ago | |
| MUSIC-AVQA-R (test) | AV-Master | Audio QA Count (Head)84.9 | 26 | 1mo ago | |
| Music-AVQA | Music-AVQA Clean Accuracy85.15 | 25 | 1mo ago | ||
| video-SALMONN 2 (test) | Miss Rate29.1 | 18 | 3mo ago | ||
| OmniVideoBench | Accuracy0.356 | 18 | 3mo ago | ||
| WorldSense | OmniSIFT | Accuracy50 | 18 | 3mo ago | |
| AVSD (test) | UniMVU | CIDEr165.1 | 15 | 7d ago | |
| MUSIC-AVQA | TASS | Audio Count Acc83.38 | 14 | 2mo ago | |
| MUSIC-AVQA | SSAM | Accuracy (V+A+L)54.68 | 12 | 2mo ago | |
| VALOR (test) | M3KG-RAG | M.J. Score44.67 | 12 | 3mo ago | |
| General AVQA Benchmarks AVQA, VALOR2, MUSIC-AVQA | VideoLLaMA2-AVCD | Accuracy (MUSIC-AVQA)81.58 | 10 | 22d ago | |
| UGC-AVQA | Gemini-3.1-pro | Average Score69.1 | 9 | 7d ago | |
| AVQA (val) | MEERKAT | Existence Accuracy88.24 | 9 | 3mo ago | |
| Daily-Omni 1 FPS | StreamOV | Metric 3070.9 | 8 | 8d ago | |
| Video Holmes 32 frames | StreamOV | SR64.4 | 8 | 8d ago | |
| Daily-Omni | Score73.6 | 8 | 2mo ago | ||
| Video-Holmes | Score59.9 | 8 | 2mo ago | ||
| Video-MME | Score75 | 8 | 2mo ago | ||
| MUSIC-AVQA balanced (test) | MEERKAT | Existential Score83.62 | 8 | 3mo ago |
