Humanoid robot outruns people, shatters human-set world record in Beijing half-marathon | Watch

In a considerable technological leap, a humanoid robot developed by a Chinese company emerged victorious in a half-marathon race in Beijing on Sunday. The robot outpaced humans during the race, setting a record finish and breaking a world record set by a human.

It was a unique sight in Beijing E-Town, with humanoid robots being spotted running alongside human runners at a half-marathon event in China, sparking excitement and curiosity.

Over 100 teams from China, Germany, France and Brazil took part in the race along with human runners.

Chinese humanoid robot breaks human's half-marathon record

Flash, the humanoid robot developed by Shenzhen Honor Smart Technology Development Co., Ltd., broke the half-marathon human record, as per Chinese media. At the 2026 Beijing E-Town half-marathon, the robot finished the course in 50 minutes and 26 seconds, outpacing the human who holds the world record.

More from Sports

Uganda's Jacob Kiplimo holds the men's half-marathon world record. He achieved it at the Lisbon Half Marathon in Portugal last month, after finishing the course in 57 minutes and 20 seconds.

Unique competition rules set during half-marathon

In terms of competition rules, robots and human runners followed the same route of 21 km but separate lanes to ensure safety, and the robot's cutoff time was set at three hours and 40 minutes, state-run Xinhua news agency reported.

The newly added format this year includes two ways of participation - remote control and autonomous navigation.

For teams in remote control, their finishing times need to be multiplied by a coefficient of 1.2. About 40 per cent of the teams adopted autonomous navigation to achieve better results.

While 'Flash' finished the fastest, China's Zhao Haijie claimed the men's title after finishing the course in an hour, seven minutes and 47 seconds. Wang Qiaoxia was crowned the winner in the women's race after finishing the half-marathon in 1:18:06.

With PTI Inputs