
Unitree
Unitree H2
- Autonomy
- IIAssisted
- Pre-release
- 75/100Promising
- Readiness
- Not assessed
- Price
- $29,900list

Unitree

Leju Robot
Up to three
All humanoid robots. Every figure below is placed against the whole class, so a gap can be read against how much the class itself varies.
The conditions each robot was assessed against, side by side. Rows marked in gold are where these machines genuinely differ.
| Condition | Unitree H2 | Leju Kuavo 5 |
|---|---|---|
| Where it operates | ||
| Home / residential | PoorPlatform targets industrial deployment only. No domestic autonomy capability disclosed. | PoorHome services are only a listed application area; no home deployment, price or channel exists. |
| Office / retail | DependsH2 is in pilot-phase industrial deployment. Commercial availability as a product remains unannounced. | DependsLeju lists commercial guide work, but no commercial deployment of Kuavo 5 is documented. |
| Warehouse / factorythey differ | GoodH2 demonstrates scripted task autonomy in factory environments with on-site safety supervision assumed. | DependsDemonstrated at Nio's EV factory, with no published results or delivery terms. |
| Primary tasks | ||
| Household chores | PoorNo domestic task autonomy has been demonstrated or claimed. | PoorNo household task results or home trials are documented for Kuavo 5. |
| Social / carethey differ | PoorH2 is positioned for task execution, not human interaction or companionship. | DependsCommercial guide work is a listed application, with no documented deployment or results. |
| Specialized jobthey differ | GoodDemonstrated in repetitive manufacturing tasks, picking, placement, line work. | DependsInterchangeable end effectors suit specific jobs, but no task success rates are published. |
| Supervision needs | ||
| Fully autonomous | PoorIndustrial deployments assume on-site operators and safety staff monitoring. | PoorNo source documents Kuavo 5 completing tasks end to end without human direction. |
| With oversightthey differ | GoodAutonomy is task-scripted; human oversight is integral to industrial pilot design. | DependsSupervised factory work matches its demonstrations, though no supervised results are published. |
| Teleoperatedthey differ | GoodH2 is actively in pilot-phase factory deployments with structured handoff workflows. | DependsA pilot would need a Leju agreement; no pricing or pilot terms are public. |
| Timeline | ||
| Ready today | PoorH2 is pre-release. No shipping date or consumer pricing has been announced. | PoorNo price, channel or delivery date is published for Kuavo 5. |
| Near-term (1–2 yrs) | DependsIf H2 commercializes within 12 months, availability will depend on Unitree's distribution strategy. | DependsLaunched November 2025 with factory demos, but no availability date has been announced. |
| Research phasethey differ | GoodH2 is currently a research and industrial pilot platform with demonstrated autonomy in controlled environments. | DependsUseful as a modular platform to follow, though specifications are not published by Leju. |
A robot being poor for a condition is a fact about fit, not a fault. “Depends” means the record names a limit worth reading, not that the answer is unknown.
None of these has shipped, so they are assessed on track record, engineering plausibility and how the demonstrations match the claims.
Never averaged into it. These describe how much the maker has disclosed, not what the machine does.
| Unitree H2 | Leju Kuavo 5 | |
|---|---|---|
| ReadinessShip-date specificity, pricing transparency, distribution and regulatory status. Published beside the number; never averaged in. | 25/100 | 25/100 |
| DisclosureHow much of the product is disclosed. Higher means fewer fundamental unknowns remain. Published beside the number; never averaged in. | 40/100 | 35/100 |
A number only means something next to the spread it sits in. Each track is the real range across every classified robot in the class, with the median marked.
Not compared, because fewer than two of these robots carry a published figure: Price, Charge time, Noise, Weight, Height.
Written on each record, and the only thing here every robot on the site carries.
What each design gives up to be good at what it is good at.
Bipedal design demands precise balance control that manufacturing environments demand; humanoid hardware cost and complexity remain unpriced.
Swappable legs, wheels and hands make one platform fit many jobs; none of those jobs has a published result yet.
Stated by the record itself. A robot being wrong for a household is a fact about fit, not a fault.
The upkeep ownership hands back to you, whatever the autonomy level says.
Classifications rest on different depths of evidence. A pre-release assessment and a verified one are not the same kind of claim.
| Robot | Evidence status | Sources reviewed | Last assessed |
|---|---|---|---|
| Unitree H2 | Not Consumer-Ready | 3 | Sep 2026 |
| Leju Kuavo 5 | Pre-Release | 3 | Sep 2026 |
Evidence status counts the sources behind a classification, not their kind. A high count can be maker documentation and price coverage, so read it as how much was reviewed rather than as independent testing. How we weigh evidence.
The full recordUnitree H2Specifications, evidence, the Fit Check in full, and every tracked change.
The full recordLeju Kuavo 5Specifications, evidence, the Fit Check in full, and every tracked change.Robovations classifies robots; it does not rank them. Nothing on this page is a recommendation, and no manufacturer influences a classification or its placement here.
Comparing across classes is allowed — the page will switch to per-class positioning and tell you it has.