AVI-Bench Audio-Visual Intelligence Benchmark
ICML 2026 · Main Conference

AVI-Bench

Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

Yaoting Wang1, Ziyi Zhang2, Wenming Tu3, Shaoxuan Xu4, Wenjie Du5, Cheng Liang3, Weijun Wang6, Yuanchao Li7, Guangyao Li6 Hao Fei8, Yuanchun Li6, Henghui Ding1, Yunxin Liu6

1 Fudan University 2 Huazhong University of Science and Technology 3 Shanghai Jiao Tong University 4 Renmin University of China 5 Nanyang Technological University 6 Tsinghua University 7 University of Edinburgh 8 University of Oxford

Leaderboard

Loading results

AVI-Index Progress

Domain-Adaptive score · 0–100

Loading trend data…

Cognition Stage Score

Loading…
Loading results…

Adaptive Intelligence Score

Loading…
Loading results…
Robot evolution from task-adaptive competence to domain-adaptive human-like audio-visual intelligence

Citation

@inproceedings{wang2026avibench,
  title     = {AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs},
  author    = {Wang, Yaoting and Zhang, Ziyi and Tu, Wenming and Xu, Shaoxuan and
               Du, Wenjie and Liang, Cheng and Wang, Weijun and Li, Yuanchao and
               Li, Guangyao and Fei, Hao and Li, Yuanchun and Ding, Henghui and
               Liu, Yunxin},
  booktitle = {Proceedings of the 43rd International Conference on Machine Learning (ICML)},
  year      = {2026}
}