Compare
Reachy 2 vs XMAN-R1
Quick verdict
Reachy 2 leads on 8 of 11 comparable rows
Reachy 2 leads on Readiness Score, Reality Score, Battery, and Price (+4 more). XMAN-R1 leads on Mobility, Autonomy, and Social Interaction.
Who should choose which?
Choose Reachy 2 if…
- You want higher readiness (86/100 vs peers) for near-term home use.
- Verified shipping and public proof matter more to you (reality score 84/100).
- Budget is a priority and Reachy 2 lists lower ($70,000+).
- Your main goal is education, which Reachy 2 targets directly.
- Strengths like manipulation and perception match how you plan to use it at home.
Choose XMAN-R1 if…
- Your main goal is conversation, which XMAN-R1 targets directly.
- Strengths like social interaction and perception match how you plan to use it at home.
| Spec | Reachy 2  Pollen RoboticsLeads 8 | XMAN-R1  KEENON RoboticsLeads 3 |
|---|---|---|
| Performance | ||
| Readiness Score | 86 | 76 |
| Reality Score | 84 | 72 |
| Data Freshness | 100% | 100% |
| Speed | Unknown | 2.9 km/h |
| Payload | 3 kg per arm | 3 kg |
| Specs | ||
| Height | 136–166 cm | 172 cm |
| Weight | 32–50 kg | 110 kg |
| Battery | 8–10 h | 3 h |
| Form | Humanoid | Humanoid |
| Availability | ||
| Price | $70,000+ | $100,000+ |
| Market Status | Limited | Limited |
| Availability | Limited | Limited |
| Countries | United States, France, Global (direct order) | China, United States |
| Intelligence | ||
| Mobility | 68 | 74 |
| Manipulation | 88 | 70 |
| Perception | 86 | 84 |
| Autonomy | 72 | 78 |
| Social Interaction | 70 | 90 |
| Home Navigation | 58 | 52 |
| Sensors | 2× IMX296 global-shutter stereo cameras, Orbbec Gemini 336 RGB-D, Luxonis OAK ToF, RPLIDAR S2, 2× lavalier mics, wheel IMUs | Multimodal fusion perception, spatial awareness, human-interaction sensing (fleet coordination stack) |
| Connectivity | Ethernet, Wi-Fi (customer network for AI) | Wi-Fi, KEENON cloud fleet platform |
| Ecosystem | ROS 2 Humble; Python SDK; Hugging Face LeRobot; Pollen-Vision perception library; VR teleoperation (Meta Quest 2/3); Docker simulation stack (Gazebo, MuJoCo) | KOM2.0 vision-language-action stack; KEENON ProS hotel domain models; Multi-robot fleet coordination with DINERBOT, KLEENBOT, BUTLERBOT, S100; KEENON App and Cloud Platform |
Green cells mark the stronger value in each row across 2 robots.