Compare

Stretch 4 vs Reachy 2

← Back to robots

Quick verdict

Reachy 2 leads on 6 of 11 comparable rows

Stretch 4 leads on Price, Mobility, Perception, and Autonomy (+1 more). Reachy 2 leads on Readiness Score, Reality Score, Payload, and Battery (+2 more).

Who should choose which?

Stretch 4
Choose Stretch 4 if…
  • Budget is a priority and Stretch 4 lists lower ($29,950).
  • You need a buy now path today while alternatives are still prototype or coming soon.
  • Your main goal is home assistant, which Stretch 4 targets directly.
  • Strengths like perception and manipulation match how you plan to use it at home.
  • You prefer a other form factor over the alternatives in this compare.
Reachy 2
Choose Reachy 2 if…
  • Your main goal is education, which Reachy 2 targets directly.
  • Strengths like manipulation and perception match how you plan to use it at home.
  • You prefer a humanoid form factor over the alternatives in this compare.
Performance
Readiness Score
84
86
Reality Score
80
84
Data Freshness
85%
85%
Speed2.2 km/hUnknown
Payload2.5 kg (extended) / 4 kg (retracted)3 kg per arm
Specs
Height160 cm136–166 cm
Weight46 kg32–50 kg
Battery8 h8–10 h
FormOtherHumanoid
Availability
Price$29,950$70,000+
Market StatusBuy NowLimited
AvailabilityLimitedLimited
CountriesUnited States, Global (direct order)United States, France, Global (direct order)
Intelligence
Mobility
82
68
Manipulation
88
88
Perception
90
86
Autonomy
74
72
Social Interaction
58
70
Home Navigation
86
58
Sensors2× hemispherical 3D LiDAR (Hesai), 3× high-res cameras, 6× laser line sensors, wrist depth camera, IMU2× IMX296 global-shutter stereo cameras, Orbbec Gemini 336 RGB-D, Luxonis OAK ToF, RPLIDAR S2, 2× lavalier mics, wheel IMUs
ConnectivityWi-Fi 5.2, Ethernet, USB expansionEthernet, Wi-Fi (customer network for AI)
EcosystemROS 2 Humble; Python SDK; Stretch Body software stack; Optional self-charging dock; Quick-release gripper tooling; Global distributor network (Japan, Korea, China)ROS 2 Humble; Python SDK; Hugging Face LeRobot; Pollen-Vision perception library; VR teleoperation (Meta Quest 2/3); Docker simulation stack (Gazebo, MuJoCo)
Green cells mark the stronger value in each row across 2 robots.