| title | ASI-Bench: At the Dawn of Artificial Superintelligence |
|---|---|
| authors | Junwei Zhou, Zhen Sun, Binyu Li, Jiangyu Zhou, Yuexi Pan, Hengyu Wang, Honghe Ren, Xiaohan Jia, Xueyang Zhou, Xiaoyu Cao, Yongchao Chen, Yuanning Feng, Junhao Wu, Cheng Zhang, Sijia Chen, Haoyu Xue, Chengsong You, Huan Wang, Koutian Wu, Peigan Gao, Jiakun Wu, Wenzhe Li, Ergan Shang, Qingyuan Zheng, Jingjing Zhou, Ruixuan Jia, Yan Xu, Hongrui Zhang, Xiao-Han Ma, Zhengxiang Cheng, Yuexing Hao, Liting Mai, Xianglin Ji, Wenjun Zhang, Zhuofan Chen, Yixiao Huang, Chi Wang, Wenyue Hua, Yilun Hao, Yuantao Zhai, Ziyan Zhao, Jingyan Xie |
| date | 2026-08-18 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2608.17271 |
| upvotes | 69 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Artificial superintelligence (ASI) requires AI to move beyond mastering existing knowledge toward exploring the unknown, creating new knowledge, and turning new ideas into verifiable results. However, the capabilities of today's AI systems are still largely built on learning, compressing, and applying existing human knowledge. Accordingly, existing benchmarks primarily test whether AI can produce correct answers based on learned knowledge, or whether it can complete tasks under extensive human guidance. We therefore introduce ASI-Bench, the first benchmark to jointly evaluate AI systems' capabilities of innovative exploration and autonomous scientific execution across general research domains, and the first to progressively withdraw human methodological guidance within the same research project to test how far AI can proceed on its own. Built by over 40 experts with the cost of 31,000+ human hours, ASI-Bench contains 60 project-level research tasks across 11 scientific domains and progressively reduces methodological guidance to test whether AI can independently select methods, conduct research, and produce verifiable results. All tasks undergo expert review, AI-assisted auditing, sandbox execution, and scorer validation. Across 18 state-of-the-art agent--model configurations, the average score drops from 50.91 with full methodological guidance to 29.10 with only the method specified and 26.62 when agents must determine the method themselves. This sharp decline shows that current systems remain heavily dependent on human guidance and are still far from autonomously conducting end-to-end, project-level scientific research. ASI-Bench is open to the world. We invite researchers and builders everywhere to contribute new tasks, challenge the limits of today's AI, and help accelerate humanity's collective path toward artificial superintelligence at https://asibench.apexin.ai/submit. |
cite
@misc{zhou2026asi,
title={ASI-Bench: At the Dawn of Artificial Superintelligence},
author={Junwei Zhou and Zhen Sun and Binyu Li and Jiangyu Zhou and Yuexi Pan and Hengyu Wang and Honghe Ren and Xiaohan Jia and Xueyang Zhou and Xiaoyu Cao and Yongchao Chen and Yuanning Feng and Junhao Wu and Cheng Zhang and Sijia Chen and Haoyu Xue and Chengsong You and Huan Wang and Koutian Wu and Peigan Gao and Jiakun Wu and Wenzhe Li and Ergan Shang and Qingyuan Zheng and Jingjing Zhou and Ruixuan Jia and Yan Xu and Hongrui Zhang and Xiao-Han Ma and Zhengxiang Cheng and Yuexing Hao and Liting Mai and Xianglin Ji and Wenjun Zhang and Zhuofan Chen and Yixiao Huang and Chi Wang and Wenyue Hua and Yilun Hao and Yuantao Zhai and Ziyan Zhao and Jingyan Xie},
year={2026},
eprint={2608.17271},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2608.17271}
}