| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| MUSIC-AVQA 1.0 (test) | Sparsify | AV Localis Accuracy85.09 | 96 | 1mo ago | |
| MUSIC-AVQA (test) | VAST | Acc (Avg)80.7 | 59 | 1mo ago | |
| AVQA | Crab+ | Accuracy92.16 | 37 | 4d ago | |
| Music-AVQA | VideoLLaMA2 | Accuracy81.3 | 33 | 1mo ago | |
| Music-AVQA | Music-AVQA Clean Accuracy85.15 | 25 | 12d ago | ||
| video-SALMONN 2 (test) | Miss Rate29.1 | 18 | 1mo ago | ||
| OmniVideoBench | Accuracy0.356 | 18 | 1mo ago | ||
| WorldSense | OmniSIFT | Accuracy50 | 18 | 1mo ago | |
| MUSIC-AVQA Bias v2.0 (test) | SHRIKE | Total Accuracy77.33 | 18 | 1mo ago | |
| MUSIC-AVQA balanced v2.0 (test) | LAST-Att | Total Accuracy75.44 | 18 | 1mo ago | |
| MUSIC-AVQA | TASS | Audio Count Acc83.38 | 14 | 1mo ago | |
| AVQA (test) | JavisGPT | Total Accuracy93.8 | 13 | 1mo ago | |
| MUSIC-AVQA-R (test) | QA-TIGER | Audio QA Count (Head)82.67 | 13 | 1mo ago | |
| MUSIC-AVQA | SSAM | Accuracy (V+A+L)54.68 | 12 | 25d ago | |
| VALOR (test) | M3KG-RAG | M.J. Score44.67 | 12 | 1mo ago | |
| AVQA (val) | MEERKAT | Existence Accuracy88.24 | 9 | 1mo ago | |
| Daily-Omni | Score73.6 | 8 | 1mo ago | ||
| Video-Holmes | Score59.9 | 8 | 1mo ago | ||
| Video-MME | Score75 | 8 | 1mo ago | ||
| MUSIC-AVQA balanced (test) | MEERKAT | Existential Score83.62 | 8 | 1mo ago | |
| Music-AVQA 2000 samples | Combined Loss | ASR Rate13.8 | 7 | 1mo ago | |
| AVQA (subset 2000 samples) | Combined Loss | ASR Accuracy96.03 | 7 | 1mo ago | |
| AVQA | Negative Language Modeling Loss | AVQA Clean Accuracy95.6 | 7 | 1mo ago | |
| Music-AVQA 30 (test) | CAT-7B-FT | Overall Accuracy84.3 | 7 | 1mo ago | |
| Music-AVQA | UniMambaMia | Original Score79.5 | 6 | 1mo ago |
