Advanced version of Gemini with Deep Think officially achieves gold-medal standard at the International Mathematical Olympiad

Acknowledgements

We thank the International Mathematical Olympiad organization for their support.

This project was a large-scale collaboration, and its success is due to the combined efforts of many individuals and teams. Thang Luong led the overall technical direction for IMO 2025 effort and co-led with Edward Lockhart on the overall coordination.

The leads and key contributors of the IMO 2025 team are the following; Dawsen Hwang, Junehyuk Jung, Jonathan Lee, Nate Kushman, Pol Moreno, Yi Tay, Lei Yu, Golnaz Ghiasi, Garrett Bingham, Lalit Jain, Vincent Cohen-Addad and Theophane Weber, Ankesh Anand, Steven Zheng, Vinh Tran, Vinay Ramasesh, Andreas Kirsch, Jieming Mao, Zicheng Xu, Wilfried Bounsi, Vahab Mirrokni, Hoang Nguyen, Fred Zhang, Mahan Malihi, Yangsibo Huang, Yuri Chervonyi, Trieu Trinh, Junsu Kim, Mirek Olšák, Marcelo Menegali, Xiaomeng Yang, Richard Song, Miklós Z. Horváth, Aja Huang, Goran Žužić.

The advanced Gemini model with Deep Think for IMO was built on foundational research from the Deep Think team with sponsorship of the GDM Thinking area, and corresponding post-training efforts including; Archit Sharma, Shubha Raghvendra, Tong He, Pei Sun, Tianhe (Kevin) Yu, Eric Ni, Siamak Shakeri, Hanzhao (Maggie) Lin, Cosmo Du, Sid Lall, Le Hou, Yuan Zhang, Yujing Zhang, Yong Cheng, Luheng He, and Chenxi Liu.

This effort was advised by Quoc Le and Pushmeet Kohli, with program management from Kristen Chiafullo and Alex Goldin.

We’d also like to thank our experts for providing data and evaluations: Insuk Seo (lead), Jiwon Kang, Donghyun Kim, Junsu Kim, Jimin Kim, Seongbin Jeon, Yoonho Na, Seunghwan Lee, Jihoo Lee, Younghun Jo, Yongsuk Hur, Seongjae Park, Kyuhyeon Choi, Minkyu Choi, Su-Hyeok Moon, Seojin Kim, Yueun Lee, Taehun Kim, Jeeho Ryu, Seungwoo Lee, Dain Kim, Sanha Lee, Hyunwoo Choi, Aiden Jung, Youngbeom Jin, Jeonghyun Ahn, Junhwi Bae, Gyumin Kim, Nam Dung Tran, Quoc Ba Can Vo, Van Huyen Nguyen, Tuan Anh Nguyen, Thanh Dat Vo, Nguyen Nam Hung Tran, Van Khai Luong, Son Vu, Son Tra Dao, Dai Dinh Phong Tran, Thanh Dat Le, Cheng-Chiang Tsai, Kari Ragnarsson, Kiat Chuan Tan, Yahya Tabesh, Hamed Mahdavi, Azin Nazari, Chu-Lan Kao, Steven Creech, Tony Feng, Daogao Liu, and Ciprian Manolescu.

Further thanks to the following people for support, collaboration, and advice; Omer Levy, Timothy Lillicrap, Jack Rae, Yifeng Lu, Heng-tze Cheng, Denny Zhou, Ed Chi, Vahab Mirrokni, Tulsee Doshi, Madhavi Sewak, Melvin Johnson, Fernando Pereira, Benoit Schillings, Koray Kavukcuoglu, Oriol Vinyals, Jeff Dean, Demis Hassabis, Sergey Brin, Jessica Lo, Sajjad Zafar, Tom Simpson, Jane Labanowski, Andy Forbes, Sean Nakamoto, Jonathan Lai, Fabian Pedregosa, Samuel Albanie, Alex Zhai, Sara Javanmardi, Divy Thakkar, YaGuang Li, Nigamaa Nayakanti, Chenjie Gu, Chenkai Kuang, Swaroop Mishra, Filipe Miguel de Almeida, Silvio Lattanzi, Ashkan Norouzi Fard, Tal Schuster, Ziwei Ji, Honglu Fan, Xuezhi Wang, Aditi Mavalankar, Tom Schaul, Rosemary Ke, Xiangzhuo Ding, Adam Brown, Emanuel Taropa, Charlie Chen, Joe Stanton, Cip Baetu, Alvin Abdagic, Federico Lebron, Ioana Mihailescu, Soheil Hassas Yeganeh, Ashish Shenoy, and Minh Giang

Finally, we thank Prof Gregor Dolinar from the IMO Board for the support and endorsement.

The IMO have confirmed that our submitted answers are complete and correct solutions. It is important to note that their review does not extend to validating our system, processes, or underlying model (see more).