Humanoid Robot Leaderboard

156 robots · ranked by XHI

#	Robot	Status	Autonomy	DoF	Payload	Speed	Conf.	XHI
126	🇪🇸 TALOSPAL Robotics	commercial	research	32	6.0 kg	0.83 m/s	high	33.9
127	🇯🇵 G1GITAI	prototype	teleoperated	21	—	—	medium	33.9
128	🇫🇷 Reachy 2Pollen Robotics (Hugging Face)	commercial	teleoperated	—	3.0 kg	—	high	33.7
129	🇨🇳 Hobbs 3Noetix Robotics	prototype	supervised-autonomy	40	—	—	low	33.6
130	🇵🇱 Protoclone V1Clone Robotics	prototype	research	200	—	—	medium	33.6
131	🇹🇼 TM Xplore ITechman Robot	prototype	supervised-autonomy	22	—	—	high	33.6
132	🇨🇳 AELOS SeriesLeju Robot	commercial	teleoperated	22	0.5 kg	—	high	33.2
133	🇰🇷 KAIST Humanoid v0.5KAIST Dynamic Robot Control & Design Lab	research	task-autonomous	—	—	—	medium	33.0
134	🇮🇹 ergoCubIstituto Italiano di Tecnologia (IIT)	research	research	54	10.0 kg	—	medium	32.7
135	🇬🇧 MesmerEngineered Arts	commercial	teleoperated	—	—	—	medium	32.4
136	🇩🇪 4NE-1 MiniNEURA Robotics	prototype	research	25	3.0 kg	—	medium	32.2
137	🇨🇳 SA01EngineAI	limited-production	research	—	—	—	medium	32.1
138	🇨🇳 AgiBot D2 MaxAgiBot (Zhiyuan Robotics)	prototype	supervised-autonomy	—	—	—	low	30.8
139	🇨🇳 DR01Deep Robotics	prototype	research	—	—	1.6 m/s	medium	28.3
140	🇨🇳 AgiBot X1 (Lingxi X1)AgiBot (Zhiyuan Robotics)	limited-production	research	34	—	—	low	26.7
141	🇺🇸 Optimus Gen 4Tesla	prototype	research	—	—	—	low	24.9
142	🇨🇳 Xiao NuoNoetix Robotics	prototype	teleoperated	32	—	—	low	23.2
143	🇯🇵 T-HR3Toyota	research	teleoperated	32	2.0 kg	—	high	23.2
144	🇨🇳 CyberOneXiaomi	prototype	research	21	1.5 kg	—	medium	22.6
145	🇨🇳 Walker C1UBTech Robotics	prototype	teleoperated	—	—	—	medium	22.2
146	🇮🇹 GENE.01Generative Bionics	prototype	research	—	—	—	low	18.5
147	🇰🇷 AMBIDEXNaver Labs	research	teleoperated	14	3.0 kg	—	medium	18.4
148	🇫🇷 NorthstarUMA	prototype	research	—	—	—	medium	18.1
149	🇪🇸 KangarooPAL Robotics	prototype	research	—	—	—	medium	17.7
150	🇸🇦 SARAQSS AI & Robotics	prototype	research	—	—	—	low	17.7

Reading the table. XHI is the weighted composite (0–100) for this category, normalised against humanoid-specific reference scales. “Autonomy” shows the demonstrated mode — teleoperated systems are capped low regardless of hardware. “Conf.” is the data-confidence grade for that robot's specs. Click any row for the full breakdown and sources.

These rankings are not comparable across categories. Each category has its own index, its own pillar weights and its own reference scales, so an XHI of 71 and a score of 71 on another leaderboard answer different questions. Only autonomy and commercial readiness are scored from ladders that mean the same thing everywhere. Why →