1X Technologies
1X NEO
- Autonomy
- IIAssisted
- Pre-release
- 63/100Plausible
- Readiness
- Known Issues
- Price
- $20,000list
Comparison1X NEO and Unitree H2
Unitree
Unitree H2
- Autonomy
- IIAssisted
- Pre-release
- 75/100Promising
- Readiness
- Not assessed
- Price
- $29,900list
Up to three
Autonomy Ladder
- IManual
- IIAssisted
- IIIConditional
- IVEnvironmental
- VGeneralized
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.
Where each one suits you.
The conditions each robot was assessed against, side by side. Rows marked in gold are where these machines genuinely differ.
| Condition | 1X NEO | Unitree H2 |
|---|---|---|
| Where it operates | ||
| Home / residentialthey differ | GoodDesigned specifically for household environments; soft-body safety profile matches residential spaces well. | PoorPlatform targets industrial deployment only. No domestic autonomy capability disclosed. |
| Office / retail | DependsCommercial deployments underway with subscription support, but scale and reliability in diverse facilities still limited. | DependsH2 is in pilot-phase industrial deployment. Commercial availability as a product remains unannounced. |
| Warehouse / factorythey differ | PoorSoft actuators and residential design do not meet industrial durability or force requirements. | GoodH2 demonstrates scripted task autonomy in factory environments with on-site safety supervision assumed. |
| Primary tasks | ||
| Household choresthey differ | GoodLight cleaning, object retrieval, and maintenance routines are primary demonstrated use cases. | PoorNo domestic task autonomy has been demonstrated or claimed. |
| Social / carethey differ | DependsOperator control enables interaction but requires real-time human piloting; autonomous presence is limited. | PoorH2 is positioned for task execution, not human interaction or companionship. |
| Specialized jobthey differ | PoorSoft actuators lack force and precision for specialized tasks like assembly, repair, or delicate handling. | GoodDemonstrated in repetitive manufacturing tasks, picking, placement, line work. |
| Supervision needs | ||
| Fully autonomous | PoorContinuous operator oversight required; not suitable for unattended autonomous operation. | PoorIndustrial deployments assume on-site operators and safety staff monitoring. |
| With oversight | GoodOperator monitoring and intervention model aligns with supervision-level expectations. | GoodAutonomy is task-scripted; human oversight is integral to industrial pilot design. |
| Teleoperated | GoodExpert-pilot subscription tier explicitly designed for operator-controlled deployment and workflow integration. | GoodH2 is actively in pilot-phase factory deployments with structured handoff workflows. |
| Timeline | ||
| Ready todaythey differ | DependsAvailable now through commercial subscription but not retail-ready; early deployments show promise but limited scale. | PoorH2 is pre-release. No shipping date or consumer pricing has been announced. |
| Near-term (1–2 yrs)they differ | GoodEngineering roadmap signals incremental autonomy improvements; pathway to higher autonomy levels documented. | DependsIf H2 commercializes within 12 months, availability will depend on Unitree's distribution strategy. |
| Research phase | GoodPre-release platform suitable for research partnerships and feasibility pilots. | GoodH2 is currently a research and industrial pilot platform with demonstrated autonomy in controlled environments. |
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.
How much the claim can be trusted.
None of these has shipped, so they are assessed on track record, engineering plausibility and how the demonstrations match the claims.
Track Record35% of score
Has this maker shipped what it demoed before, on schedule, with the promised capability?
5885
- 1X NEO58
- Unitree H285
28median 70 across 90 pre-release records100
Engineering35% of score
Are the demonstrated capabilities achievable in shipping form, or do they need breakthroughs not in evidence?
66100
- 1X NEO66
- Unitree H2100
35median 70 across 101 pre-release records100
Demo Match30% of score
What has been shown to work, against what is claimed in marketing.
66100
- 1X NEO66
- Unitree H2100
30median 66 across 101 pre-release records100
Published beside the number
Never averaged into it. These describe how much the maker has disclosed, not what the machine does.
| 1X NEO | Unitree H2 | |
|---|---|---|
| ReadinessShip-date specificity, pricing transparency, distribution and regulatory status. Published beside the number; never averaged in. | 90/100 | 25/100 |
| DisclosureHow much of the product is disclosed. Higher means fewer fundamental unknowns remain. Published beside the number; never averaged in. | 55/100 | 40/100 |
How far apart is a long way?
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.
Price20 with a published figure
$20,000$29,900
- 1X NEO$20,000
- Unitree H2$29,900
$1,385median $22,500$250,000
Runtime40 with a published figure
240 min180 min
- 1X NEO240 min
- Unitree H2180 min
60 minmedian 180 min720 min
Weight52 with a published figure
66 lbs154.3 lbs
- 1X NEO66 lbs
- Unitree H2154.3 lbs
26.5 lbsmedian 143 lbs661.4 lbs
Height54 with a published figure
66 in71.7 in
- 1X NEO66 in
- Unitree H271.7 in
34.7 inmedian 67 in86.6 in
Not compared, because fewer than two of these robots carry a published figure: Charge time, Noise.
What the numbers leave out.
Written on each record, and the only thing here every robot on the site carries.
The trade-off
What each design gives up to be good at what it is good at.
1X NEO
Tendon-driven compliance maximizes safety in shared spaces but leaves precision and contact-sensitive work unproven; with a published 154 lb lift and 18 lb per-arm payload, raw force is not what the design gives up.
Operator partnership ensures task flexibility and professional support but requires continuous human labor cost.
A $499 per month plan makes a home humanoid reachable without a $20,000 purchase, but keeps the robot on an ongoing subscription rather than owned outright.
Unitree H2
Bipedal design demands precise balance control that manufacturing environments demand; humanoid hardware cost and complexity remain unpriced.
Who each one is wrong for
Stated by the record itself. A robot being wrong for a household is a fact about fit, not a fault.
1X NEO
- Buyers expecting the robot to pay for itself
- At $20,000 outright or $499 per month, the published task set does not yet cover enough household work to argue on cost. NEO is bought for what it does, not for what it saves.
- Outdoor or weather-exposed use
- NEO is an indoor household robot. 1X publishes no outdoor, moisture or temperature rating, and its vision-only sensing is characterized for indoor spaces.
- Precision or damage-sensitive work
- Force is not the constraint: 1X publishes a 154 lb lift, 55 lb carry and 18 lb per-arm payload for a 66 lb robot. What is unproven is precision and contact-sensitive handling, so assembly, delicate objects and damage-sensitive tasks sit outside the published task set.
- Buyers who need a fixed task list at delivery
- 1X describes NEO's skills as expanding through Redwood AI updates, and anything outside what it has learned falls to a booked Expert session. A buyer who needs a defined capability set on day one does not have one.
- Privacy-sensitive households
- NEO's cameras run continuously for its own perception, and a 1X Expert can connect during a scheduled session and see the home through the robot. 1X notifies the owner while a session is active, but a camera-equipped robot with a remote-assist path is still a recording device inside the house.
Unitree H2
- Consumer home automation or domestic assistance
- Unitree publishes no domestic capability for H2: no cleaning, no fetching, no household task, and no autonomy that would run one. It is sold direct at $29,900 to anyone who orders it, so the barrier is capability, not availability.
- Any task that has to be completed unattended
- Unitree documents no autonomous task execution for H2, in structured environments or anywhere else. What is published is locomotion and whole-body control. Anything past that is software the buyer writes.
What stays your job
The upkeep ownership hands back to you, whatever the autonomy level says.
1X NEO
- After every use: Visual inspection of soft actuators for deformation or damage.
- Weekly: Sensor and camera lens cleaning for visual fidelity during teleop.
- Monthly: Joint and actuator deep clean to remove household dust and debris.
- Every 3-6 months: Firmware and software updates, operator training refresher on new features.
- Annually: Professional actuator wear inspection and battery degradation assessment by 1X.
- As needed: Emergency stop testing and safety system verification.
Unitree H2
- After every use: Inspect joints, shell panels and fasteners after dynamic-motion sessions; routines at that intensity load the frame far harder than walking does.
- After every use: Recharge between sessions. Unitree’s store page publishes no battery capacity or runtime figure for the H2, so session planning runs on observed runtime rather than a spec.
- As needed: Apply OTA updates. Unitree states the H2’s algorithms evolve continuously via OTA; no cadence or public changelog accompanies them.
- As needed: Actuator, joint or structural service through Unitree or an authorized reseller; no parts list or service interval is published for the H2.
- As needed: Consult Unitree’s H2 user manual for operating procedures; no maintenance schedule appears in Unitree’s accessible web material for the H2.
How much each of these is standing on.
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 |
|---|---|---|---|
| 1X NEO | Pre-Release | 12 | Sep 2026 |
| Unitree H2 | Not Consumer-Ready | 4 | 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.
Keep going.
The full record1X NEOSpecifications, evidence, the Fit Check in full, and every tracked change.
The full recordUnitree H2Specifications, 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.
Add a robot
Comparing across classes is allowed — the page will switch to per-class positioning and tell you it has.