AI Paper Atlas

Research map / Benchmarks / MUSIC-AVQA

MUSIC-AVQA leaderboard

10 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on MUSIC-AVQA. Best accuracy: 85.01 (AV-Reasoner-Thinking, CVPR 2026).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

MUSIC-AVQA · accuracy

10 papers, each with its best reported number for its own method; higher is better.

#accuracy ↑MethodPaperTopic
185.01AV-Reasoner-Thinking
Ola-Omni-7B
AV-Reasoner: Improving and Benchmarking Clue-Grounded Audio-Visual Counting for MLLMs
CVPR 2026 · Table 3
Video-language understanding
279.1VideoLLaMA2-AV + MAD
VideoLLaMA2-AV-7B
MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models
CVPR 2026 · Table 4
Cross-modal learning
378.9VALOR_LVALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset
TPAMI 2024 · Table 4
Cross-modal learning
478.69Ourshf
DeBERTa-V2
Querying as Prompt: Parameter-Efficient Learning for Multimodal Language Model
CVPR 2024 · Table 2
CLIP and zero-shot
578.42PSOT-L
CLIP-L, CLAP
Patch-level Sounding Object Tracking for Audio-Visual Question Answering
AAAI 2025 · Table: Comparison with large-s
Tracking
677.62QA-TIGERQuestion-Aware Gaussian Experts for Audio-Visual Question Answering
CVPR 2025 · Table 2
Visual question answering
776.7Audio Flamingo 3
Qwen2.5-7B
Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models
NeurIPS 2025 · Table 1
Language, safety and interpretability
875.71MokA
LLaMA2
MokA: Multimodal Low-Rank Adaptation for MLLMs
NeurIPS 2025 · Table 1
Cross-modal learning
973.6Music Flamingo
Audio Flamingo 3
Music Flamingo: Scaling Music Understanding in Audio Language Models
ICLR 2026 · Table 1
Language, safety and interpretability
1071.53Our methodLearning To Answer Questions in Dynamic Audio-Visual Scenarios
CVPR 2022 · Appendix: Modeling with motion
Visual question answering

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.