How We Score Robots

Our Scoring Methodology

Every robot on RobotTesters is evaluated using a transparent, data-driven framework. Scores range from 1 (worst) to 10 (best) per subcategory and are combined into a final 0–100 overall score through weighted averages — no subjective impressions, no sponsored rankings. Each robot family (humanoid, robot vacuum, lawn mower, window cleaner, pool cleaner, companion and pet) is scored against a dedicated set of categories tailored to what actually matters for that kind of robot — pick a tab below to see its scoring scheme.

Last updated: April 2026

Score rating scale (applies to every robot family)

80–100 Excellent
70–79 Very Good
60–69 Good
50–59 Average
0–49 Below Average

Mixed review model: hands-on tested vs specs-based

Not every robot in our database has been physically tested. Some scores are derived from publicly available specifications and verified secondary sources while we work to get hands-on time. We make this distinction explicit on every review — RTINGS, Consumer Reports and Wirecutter all do this for the same reason: a number without context is misleading.

Hands-on tested

The robot was reviewed in person by our team. Every subcategory — including those that require physical use (response naturalness, movement quality, setup, app control, durability under real conditions) — has a primary-source score. The full score is shown without an asterisk.

Specs-based review

Score derived from manufacturer datasheets, verified demo footage and cross-referenced technical documentation. Subcategories that cannot be honestly judged without physical use are marked Pending hands-on and excluded from the weighted average — the remaining weights are renormalised. The overall score is shown with an asterisk * and a partial-score note.

Specs-based reviews exist so the comparator stays useful even before we get every robot in the lab. When we do get hands-on time, the review is upgraded and the date of the change is recorded in the JSON-LD dateModified field. If you want to filter out specs-based reviews in the comparator, use the Show only hands-on tested toggle on the comparison page.

Humanoid robots

How the overall score is calculated

Each robot is assessed across 5 main categories, each split into weighted subcategories. A weighted average inside each category produces a category score (1–10). Those category scores are then combined with their respective category weights to produce the final 0–100 score (category score × 10).

Mobility & Performance 20 %
Intelligence & Autonomy 20 %
Build Quality & Hardware 16 %
Value for Money 35 %
Developer Experience 9 %

1. Mobility & Performance

20% of final score

Mobility is the foundation of any useful robot. This category measures how fast, how far, how much and how well a robot moves through the physical world. For humanoids in particular, locomotion capability is the single biggest factor separating research toys from deployable machines. The category carries the highest weight alongside Intelligence because physical versatility directly determines real-world usefulness.

Max Speed
The top continuous walking or running speed achievable by the robot under controlled conditions, expressed in metres per second (m/s). Higher speeds expand the robot's operational scope from logistics and security patrol to dynamic physical tasks.
  • 1–3: Below 0.5 m/s — barely useful for dynamic tasks.
  • 4–6: 0.5–1.5 m/s — adequate for slow-paced service work.
  • 7–9: 1.5–2.5 m/s — competitive for most industrial use cases.
  • 10: 3.0 m/s or above — world-class bipedal locomotion.
25%
of category
Payload Capacity
The maximum load the robot can safely carry or manipulate, typically via its arms or hands. Payload directly determines whether a robot can assist with real physical labour — from moving boxes in a warehouse to handing objects in a home environment.
  • 1–3: Under 2 kg — limited to handling very light objects.
  • 4–6: 2–8 kg — suitable for household or light industrial tasks.
  • 7–9: 8–20 kg — strong enough for most industrial manipulation.
  • 10: 25 kg or above — heavy-duty industrial-grade capability.
20%
of category
Battery Life
Continuous operational time on a single charge under typical working conditions. Short battery life is a critical bottleneck for deployment — most real-world workflows require at least two hours of uninterrupted operation. Robots with hot-swappable batteries receive a bonus in this subcategory.
  • 1–3: Under 1 hour — insufficient for most deployments.
  • 4–6: 1–2 hours — marginal; acceptable only with swap capability.
  • 7–9: 2–4 hours — practical for extended operational shifts.
  • 10: 4+ hours or hot-swap enabled — deployment-ready endurance.
30%
of category
Terrain Adaptability
How well the robot handles surfaces and environments beyond flat indoor floors — stairs, ramps, uneven ground, thresholds and outdoor terrain. This subcategory receives the second-highest weight because real-world environments are rarely flat.
  • 1–3: Flat indoor surfaces only; stumbles on minor obstacles.
  • 4–6: Handles gentle ramps and thresholds; no outdoor capability.
  • 7–9: Navigates stairs, uneven ground and moderate outdoor terrain.
  • 10: Robust outdoor locomotion including rough terrain and recovery from falls.
25%
of category

2. Intelligence & Autonomy

20% of final score

Raw physical capability is meaningless without the cognitive layer to direct it. This category evaluates how smart, perceptive and self-sufficient a robot is. As LLMs and AI stacks become embedded directly in robotic hardware, intelligence is increasingly the differentiator between robots that require constant operator intervention and those that can execute multi-step tasks independently.

AI Capabilities
The depth and breadth of onboard or tightly integrated AI — including computer vision, natural language processing, object recognition, large language model (LLM) integration, and real-time decision making. This carries the highest weight in the category because it defines the robot's upper bound of autonomous behaviour.
  • 1–3: Basic scripted or teleoperated responses only.
  • 4–6: Pre-trained perception models; limited generalisation.
  • 7–9: Strong vision + voice AI, partial LLM integration, real-time inference.
  • 10: Full onboard LLM, multi-modal AI, generalised task reasoning.
30%
of category
Sensor Suite
The quantity, quality and diversity of sensors available to the robot — depth cameras, LiDAR, IMUs, microphones, RGB cameras, tactile sensors, and more. A richer sensor suite means more data inputs for AI models and greater situational awareness in complex real-world environments.
  • 1–3: Basic RGB camera and IMU only.
  • 4–6: Stereo depth or structured-light sensors; basic obstacle detection.
  • 7–9: Multiple depth cameras, voice recognition, comprehensive SLAM inputs.
  • 10: 360° LiDAR, multi-array microphones, tactile sensing, full sensor fusion.
25%
of category
Autonomous Navigation
The robot's ability to plan routes, avoid obstacles, localise itself and reach destinations without continuous human input. This subcategory evaluates both the navigation stack (SLAM, path planning) and the robustness of that system in unstructured, dynamic environments.
  • 1–3: Teleoperated only; no autonomous movement.
  • 4–6: Semi-autonomous; requires pre-mapping or operator supervision.
  • 7–9: Full autonomous navigation in known environments; dynamic obstacle avoidance.
  • 10: Self-mapping and autonomous navigation in unknown, dynamic environments.
25%
of category
Task Learning
The capacity of the robot to acquire new skills — either through imitation learning, reinforcement learning, teleoperation recording, or LLM-guided instruction. Robots that can learn new tasks without requiring custom code deployments are significantly more versatile and future-proof.
  • 1–3: Fixed, hardcoded behaviours only.
  • 4–6: Basic imitation via teleoperation recording; limited generalisation.
  • 7–9: Reinforcement learning or imitation learning with cloud pipeline.
  • 10: On-device continual learning with zero-shot generalisation via LLM.
20%
of category

3. Build Quality & Hardware

16% of final score

Great software running on fragile or poorly engineered hardware will not survive deployment. This category assesses the physical engineering of the robot — the materials it is built from, how many axes of movement it has, and how rigorously safety is designed into the platform. It intentionally does not dominate the overall score because hardware quality, while essential, is a hygiene factor rather than a differentiator in 2024–2025.

Durability & Materials
The quality and longevity of the structural materials used — aluminium alloys, carbon fibre composites, high-grade plastics, and waterproofing or dust resistance ratings. Durable robots survive real-world abuse, reduce downtime and lower total cost of ownership.
  • 1–3: Cheap plastics; fragile joints; no environmental protection.
  • 4–6: Mixed materials; adequate for lab conditions but not field work.
  • 7–9: Aluminium alloy or reinforced composites; robust for industrial use.
  • 10: Aerospace or military-grade materials; full IP-rated environmental sealing.
35%
of category
Degrees of Freedom (DOF)
The total number of independently controllable joints across the robot's body. Higher DOF enables more dexterous manipulation, more natural human-like movement, and greater versatility for complex physical tasks. This metric is especially important for hand and arm design.
  • 1–3: Under 12 DOF — very limited range of motion.
  • 4–6: 12–20 DOF — sufficient for basic bipedal locomotion.
  • 7–9: 21–35 DOF — capable of complex manipulation alongside locomotion.
  • 10: 36+ DOF — full dexterous hands plus rich body articulation.
30%
of category
Safety Features
The mechanisms in place to protect people, property and the robot itself during operation. This includes force-torque limiting, emergency stop systems, collision detection, compliance joints, safety certifications, and the overall design philosophy around human–robot interaction in shared spaces.
  • 1–3: No meaningful safety features; unsafe for human-adjacent operation.
  • 4–6: Basic E-stop; software collision avoidance only.
  • 7–9: Force-torque control, hardware compliance, E-stop, safety certifications.
  • 10: Full ISO/CE safety certification; zero-force backdrivable joints; redundant stop systems.
35%
of category

4. Value for Money

35% of final score

A robot that scores perfectly on performance but costs five million dollars serves almost no one. This category contextualises capability against real-world affordability, using a simple benchmark: can this robot justify its price by replacing a US worker who earns the same amount annually? A $16,000 robot is measured against a $16,000-per-year laborer; a $110,000 robot against a $110,000-per-year professional. This category also evaluates post-purchase support structures and how easily buyers can actually acquire the robot. At 35% of the final score, it is the single most influential category in our methodology — reflecting that purchase ROI is the primary gating factor for most buyers.

Price / Performance Ratio
We benchmark a robot's purchase price against the annual salary of a US worker who performs equivalent tasks. A robot priced at $16,000 is held to the standard of a $16,000-per-year worker; one priced at $110,000 must justify its cost against a $110,000-per-year professional. This framing reflects the real deployment decision buyers face: is it cheaper to buy this robot or hire a human for the same job? A robot that cannot match the output of a human at its price-equivalent salary level scores poorly regardless of its raw technical specification.
  • 1–3: Cannot match the output of a human earning the robot's purchase price annually.
  • 4–6: Partially matches the equivalent human — workable but not compelling ROI.
  • 7–9: Reliably replaces or augments a human at the equivalent salary level.
  • 10: Clearly outperforms the equivalent-salary human across all relevant tasks.
30%
of final score
Warranty & Support
The manufacturer's warranty terms, availability of spare parts, official repair channels, and the quality of post-sales technical support. For high-cost robots, the absence of solid support infrastructure dramatically increases total cost of ownership and operational risk.
  • 1–3: No formal warranty; no spare part availability.
  • 4–6: Standard limited warranty; email support only.
  • 7–9: Multi-year warranty, available parts, responsive technical support.
  • 10: Comprehensive warranty, on-site service option, dedicated account support.
2.5%
of final score
Market Availability
How easily a buyer can actually purchase the robot — whether it is available globally, restricted to specific markets or specific customer types (e.g. institutions only), or only available via waitlist or pre-order. Availability constraints directly impact a robot's practical usefulness regardless of specification.
  • 1–3: Pre-order only or limited to select institutional buyers.
  • 4–6: Available in select regions; purchase process complex.
  • 7–9: Available via authorised distributors in major markets.
  • 10: Global direct sale with immediate fulfilment and clear pricing.
2.5%
of final score

5. Developer Experience

9% of final score

Robots are platforms, not appliances. The richness of the software ecosystem around a robot determines how quickly researchers and engineers can build new capabilities on top of it. This category carries the lowest weight (9%) because most end-users will not write code — but for the research and developer community it is a crucial signal. Robots with strong developer ecosystems compound in value over time as the community contributes new skills and tools.

SDK & APIs
The completeness and openness of the software development kit provided — including ROS/ROS2 support, Python/C++ bindings, low-level joint control APIs, simulation environments, and any restrictions on what parts of the system are accessible to third-party developers.
  • 1–3: Proprietary, closed ecosystem with no public SDK.
  • 4–6: Partial SDK; some features locked behind proprietary layers.
  • 7–9: Full ROS2 SDK with active maintenance; simulation environment available.
  • 10: Fully open SDK, ROS2 + custom APIs, active releases, simulation + hardware in the loop.
50%
of category
Documentation & Community
The quality and depth of official documentation (API references, tutorials, deployment guides) combined with the size and activity of the developer community — GitHub repositories, forums, Discord servers, academic papers, and third-party tutorials. A strong community multiplies the practical value of any SDK.
  • 1–3: Sparse or no documentation; no public community presence.
  • 4–6: Basic documentation available; small community with infrequent activity.
  • 7–9: Comprehensive docs, active GitHub, recurring community contributions.
  • 10: World-class documentation, large open-source community, research paper ecosystem.
50%
of category
Robot vacuums

How a robot vacuum's overall score is calculated

Robot vacuums are scored across 5 categories designed around the only thing that ultimately matters: a clean floor with the least possible human intervention. Cleaning power and the autonomy of the navigation system together drive 55% of the final score, with ease of use, build quality and value filling out the rest.

Cleaning Performance30 %
Navigation & Mapping25 %
Ease of Use20 %
Build Quality15 %
Value for Money10 %

1. Cleaning Performance

30% of final score

The actual cleaning result. Suction strength, mopping capability and how long the robot can keep going before the dustbin or tank become the bottleneck.

Suction Power
Raw vacuum strength, measured in Pa. Higher Pa lifts more embedded dirt from carpets and corners.
  • 1–3: Under 2,000 Pa — only adequate for very light surface dust.
  • 4–6: 2,000–4,000 Pa — solid hard-floor cleaning, weak on rugs.
  • 7–9: 4,000–7,000 Pa — strong all-rounder, handles most carpets.
  • 10: 7,000+ Pa — class-leading deep-clean performance.
40%
of category
Mopping Quality
Whether the robot mops, how it does it, and whether the mop pad is kept clean automatically. Hot-water washing and auto-refill push this score to the top.
  • 1–3: No mopping function or static drag-pad only.
  • 4–6: Basic vibrating or rotating mop, manual pad cleaning.
  • 7–9: Auto-wash mop pad with downward pressure.
  • 10: Hot-water mop wash + auto-refill water tank at the dock.
35%
of category
Dustbin & Tank Capacity
Onboard dustbin size combined with auto-empty docking capability. Larger bins and longer auto-empty cycles mean less human intervention.
  • 1–3: Small bin (<300 ml), no auto-empty.
  • 4–6: 300–500 ml bin, no auto-empty.
  • 7–9: Auto-empty dock with 30–45 day cycle.
  • 10: Auto-empty + 60-day bag cycle and large 2L+ dock.
25%
of category

2. Navigation & Mapping

25% of final score

How smartly the robot moves around the home. Better mapping tech and obstacle avoidance translate directly into fewer missed spots and fewer cables eaten by mistake.

Mapping Technology
The sensor stack used to build and remember the home's floor plan. Random bumping is the worst case; LiDAR + reactive 3D is the gold standard.
  • 1–3: Random / bump navigation, no persistent map.
  • 4–6: Gyroscope or single-camera mapping, single floor only.
  • 7–9: LiDAR with multi-floor maps and saved zones.
  • 10: LiDAR + reactive 3D / structured-light fusion, real-time updates.
35%
of category
Obstacle Avoidance
How the robot reacts to cables, socks, pet waste, slippers and furniture legs in real time.
  • 1–3: Bumper-only — collides then turns.
  • 4–6: IR or single-camera — avoids large objects.
  • 7–9: Structured-light or AI vision identifying common categories.
  • 10: Multi-class AI vision (cables, pet mess, socks, toys) with learning over time.
35%
of category
Auto-Docking & Self-Empty
Reliability of returning to base, plus what the dock automates: emptying, mop washing, water refill.
  • 1–3: Manual placement on dock or unreliable return.
  • 4–6: Reliable auto-return for charging only.
  • 7–9: Auto-dock with auto-empty bin or auto-mop wash.
  • 10: All-in-one dock: auto-empty + mop wash + water refill + dry.
30%
of category

3. Ease of Use

20% of final score

How frictionless the robot is to live with day to day — app polish, smart-home integration, and how rarely you need to actually touch it.

App & Smart Home
App quality plus integration with Alexa, Google Assistant and Apple HomeKit / Siri. Considers stability, latency, and the depth of voice commands.
40%
of category
Setup & Maintenance
First-run setup time, plus ongoing chores: emptying bins, washing mop pads, replacing brushes and filters. Automation at the dock pushes this score up.
35%
of category
Scheduling & Zones
Granularity of scheduling: per-room, per-zone, no-go zones, virtual walls, multi-floor saved maps and pet-mode logic.
25%
of category

4. Build Quality

15% of final score

How long the robot will keep working. Anti-tangle rollers, replaceable parts, and the manufacturer's after-sales commitment.

Build & Durability
Materials, brush design (anti-tangle, dual roller), motor longevity and overall fit and finish. A 1,000-hour design is treated very differently from a disposable one.
50%
of category
Warranty & Support
Length of warranty, availability of spare parts (brushes, filters, batteries), and the responsiveness of brand support channels.
50%
of category

5. Value for Money

10% of final score

What you actually get per dollar, plus how easy it is to buy. A genuinely competitive robot at $400 can score better than a flagship at $1,500.

Price / Performance
Specifications and real-world cleaning result benchmarked against the robot's price tier. A weak performer at a premium price scores low; a strong performer at a budget price scores high.
70%
of category
Market Availability
How easy it is to buy: global retail availability, Amazon presence, official local distributors and import logistics.
30%
of category
Robot lawn mowers

How a robot lawn mower's overall score is calculated

Robot lawn mowers are scored across 5 categories that combine cutting capability with the realities of an outdoor product: weather, slopes, theft and a multi-hour install. Cutting and navigation/safety together account for 55% of the final score.

Cutting Performance30 %
Navigation & Safety25 %
Ease of Use20 %
Build Quality15 %
Value for Money10 %

1. Cutting Performance

30% of final score

Lawn size handled, what slopes the mower can climb, and how clean the cut is week over week.

Area Coverage
Maximum lawn area the mower can keep in good condition without overrun.
  • 1–3: Up to 300 m² — small urban gardens only.
  • 4–6: 300–800 m² — average suburban garden.
  • 7–9: 800–1,500 m² — large garden capacity.
  • 10: 1,500+ m² — estate / commercial-grade.
40%
of category
Slope Handling
Maximum gradient (in %) the mower handles reliably without slipping or stalling.
  • 1–3: Under 20% slope — flat lawns only.
  • 4–6: 20–30% — gentle slopes.
  • 7–9: 30–40% — moderate hills.
  • 10: 45%+ — steep terrain, four-wheel-drive class.
35%
of category
Cut Quality & Consistency
Blade type (razor pivoting blades vs. fixed), mulching effect on lawn health, and how even the result is over a full season.
25%
of category

2. Navigation & Safety

25% of final score

How the mower stays inside your lawn, doesn't get stolen, and avoids running in conditions it shouldn't.

Boundary Technology
How the mower knows where to mow. Buried wires are reliable but install-heavy; GPS / RTK and vision-based wireless systems are the future.
  • 1–3: Boundary wire only, no GPS.
  • 4–6: Boundary wire + basic GPS tracking.
  • 7–9: Wireless GPS or RTK system, no wire required.
  • 10: Multi-sensor (RTK + vision) wireless boundary with cm-level accuracy.
40%
of category
Anti-Theft & Security
PIN code, alarm, GPS tracking, lift sensors and account-level security against unauthorised pairing.
30%
of category
Weather Sensing
Rain sensors, IP rating and the ability to skip mowing in wet conditions to avoid wheel damage and uneven cuts.
30%
of category

3. Ease of Use

20% of final score

How painful the install is, how good the app is, and how easy it is to set a weekly schedule and forget about it.

App & Remote Control
App polish, remote start/stop, manual control mode, integration with smart home assistants and notifications.
40%
of category
Installation Simplicity
How long the initial setup takes — boundary wire installation can take 3–4 hours; wire-free GPS systems can be set up in under an hour.
  • 1–3: 4+ hours of wire installation required.
  • 4–6: 2–4 hours with assistance.
  • 7–9: Under 1 hour, wire-free.
  • 10: 15–30 min plug-and-play with auto-mapping.
35%
of category
Scheduling
Hour-by-hour scheduling, multi-zone scheduling, and ability to skip on rainy days or quiet hours automatically.
25%
of category

4. Build Quality

15% of final score

Outdoor robots have to survive years of rain, sun, dirt and the occasional kick. This category measures how prepared they are.

Weatherproofing & Durability
IP rating, UV-resistant materials, sealed electronics, blade durability and winter-storage tolerance. IP44+ is the practical minimum.
50%
of category
Warranty & Support
Warranty length (1, 2, 3 years), spare blade and battery availability, and quality of dealer / brand support during the lifetime of the mower.
50%
of category

5. Value for Money

10% of final score

Cost benchmarked against capability and ease of acquisition.

Price / Performance
Total spec set (lawn size, slope, navigation tech, weatherproofing) compared against the mower's price tier.
70%
of category
Market Availability
Global availability, dealer network depth, and ease of getting professional installation where the mower is sold.
30%
of category
Window-cleaning robots

How a window-cleaning robot's overall score is calculated

Window cleaners are scored across 5 categories with safety treated as a first-class concern: a robot that falls off a third-floor window is a failure, no matter how well it cleans. Cleaning quality plus safety/reliability together account for 60% of the final score.

Cleaning Performance35 %
Safety & Reliability25 %
Ease of Use20 %
Build Quality15 %
Value for Money5 %

1. Cleaning Performance

35% of final score

How well the robot actually cleans glass: pattern coverage, water and detergent control, and edge / frame detection that prevents falls.

Coverage Efficiency
How completely the robot covers the glass surface. Smart pattern algorithms (Z-shape, N-shape) outperform random.
40%
of category
Water & Detergent Management
Onboard tank capacity, automatic spraying, and post-clean drying to leave a streak-free finish.
35%
of category
Edge & Frame Detection
Sensors that detect window frame and edge — the difference between a clean window and a robot on the lawn.
25%
of category

2. Safety & Reliability

25% of final score

Whether the robot stays on the window when something goes wrong — power loss, slippery glass or the cable snags.

Adhesion & Fall Prevention
Vacuum suction strength, redundant suction systems and detection of failed adhesion before the robot falls.
45%
of category
Safety Rope
Length, breaking-strength and ease of attaching the safety tether — last line of defence if suction fails.
30%
of category
Power Backup
Internal battery / UPS that keeps the suction motor running long enough to reach a safe position if mains power is cut.
25%
of category

3. Ease of Use

20% of final score

How quickly you can attach it, start a clean and choose between framed and frameless glass modes.

Setup & Attachment
Time to attach the robot to glass, mount the safety rope and refill the water tank for a session.
40%
of category
App & Remote Control
Companion app quality and remote-control responsiveness. Voice control via Alexa / Google Home where supported.
35%
of category
Cleaning Modes
Variety of supported modes — framed glass, frameless glass, mirror, tile — and how much they really help in practice.
25%
of category

4. Build Quality

15% of final score

Materials, motor longevity and warranty backing — a piece of glass-mounted hardware needs to keep working for years.

Build & Durability
Housing materials, motor lifetime, microfibre pad construction and resistance to detergent residue.
50%
of category
Warranty & Support
Warranty length and availability of spare pads, microfibres, batteries and replacement suction motors.
50%
of category

5. Value for Money

5% of final score

Window cleaners are a niche category, so price weighs less than safety and clean quality — but it still matters.

Price / Performance
Capability per dollar against the small but growing window-cleaning robot field.
70%
of category
Market Availability
Where the unit is sold, and how long it typically takes to ship to most markets.
30%
of category
Robotic pool cleaners

How a robotic pool cleaner's overall score is calculated

Pool cleaners are scored across 5 categories that focus on full coverage of the pool surface, the efficiency of the cycle, and survival in chlorinated water for years. Cleaning coverage plus efficiency account for 60% of the final score.

Cleaning Coverage35 %
Efficiency & Performance25 %
Ease of Use20 %
Build Quality15 %
Value for Money5 %

1. Cleaning Coverage

35% of final score

Whether the robot reaches every surface that matters: floor, walls, the waterline ring, and how well it captures fine debris.

Floor Cleaning Quality
How thoroughly the floor is scrubbed and how well the brushes lift dirt off textured pool surfaces.
40%
of category
Wall & Waterline Coverage
Ability to climb walls, scrub the waterline tile (where the most visible dirt accumulates), and detach cleanly.
35%
of category
Debris & Fine Particles
Capture of leaves, sand, algae and pollen-grade fines, plus how clogged the filter gets within a single cycle.
25%
of category

2. Efficiency & Performance

25% of final score

How long a full cycle takes, how good the filtration is, and whether the navigation is methodical or random.

Cycle Time
Time to complete a full pool cleaning cycle. Shorter cycles mean less energy use and more flexibility around pool use.
35%
of category
Filtration System
Filter cartridge / basket capacity, micron rating and how easy the filter is to clean. Multi-stage filters score higher.
35%
of category
Navigation Pattern
Random vs. CleverClean / scanning algorithms that map the pool and avoid missing spots or repeating tracks.
30%
of category

3. Ease of Use

20% of final score

How easy it is to drop in, schedule, and clean afterwards. Pool cleaners live a hard life and the human side has to be effortless.

Deployment & Retrieval
Weight, the presence of a pull-cord retrieval system or caddy, and how quickly water drains when removed.
40%
of category
Scheduling
Onboard timer, app scheduling, weekly programming and the ability to delay-start cycles.
35%
of category
Maintenance
Filter cleaning frequency, top vs. bottom-loading filter design, and seasonal storage requirements.
25%
of category

4. Build Quality

15% of final score

Years of submersion in chlorinated water destroy bad designs fast. Materials, sealing and warranty are critical.

Corrosion Resistance & Materials
Corrosion-resistant motors, salt-pool compatibility, UV-stable plastics and seals designed for permanent submersion.
50%
of category
Warranty & Support
Multi-year warranties (2–3 years) and access to spare brushes, tracks, drive belts and motors.
50%
of category

5. Value for Money

5% of final score

Pool robots are a long-term purchase, so value is weighted lightly: pure capability and durability dominate.

Price / Performance
Pool size handled and feature set vs. price tier. Premium models double up with smart-app and waterline coverage.
70%
of category
Market Availability
Availability through pool-supply distributors, warranty service network, and ease of importing into a given country.
30%
of category
Companion robots

How a companion robot's overall score is calculated

Companion robots are scored across 5 categories where conversation quality and social interaction together carry the most weight. A companion robot that can't hold a meaningful conversation or read a room is missing the whole point — even if the hardware is excellent.

Conversation Quality25 %
Social Interaction25 %
Ease of Use20 %
Build Quality15 %
Value for Money15 %

1. Conversation Quality

25% of final score

Whether you can actually talk with the robot, how natural the responses feel, and whether it remembers anything from previous chats.

LLM Integration
Quality of the language model behind the conversation. Modern LLM integration is the single biggest jump a companion robot can make.
  • 1–3: Pre-canned responses, simple keyword matching.
  • 4–6: Basic NLU with limited intent detection.
  • 7–9: Cloud LLM integration (GPT-class) with multi-turn dialog.
  • 10: State-of-the-art LLM with personalised tone and on-device fallback.
40%
of category
Response Naturalness
Voice quality, prosody, latency and how human-like the timing of replies feels.
35%
of category
Long-term Memory
Persistent memory of names, preferences, past conversations and the user's emotional context across sessions.
25%
of category

2. Social Interaction

25% of final score

How the robot reads the user's mood and expresses itself through movement, sound and animation.

Emotion Recognition
Facial-expression analysis, voice tone detection, and the ability to react to a user that's clearly upset, excited or bored.
40%
of category
Physical Expression
Range of motions and animations (head tilts, eye animations, gestures) that convey personality.
35%
of category
User Engagement
How interesting the robot stays after the first week — proactive interactions, surprise moments, mood-based behaviour shifts.
25%
of category

3. Ease of Use

20% of final score

How quickly the robot is up and running, how good its app is, and how often the manufacturer pushes meaningful updates.

Setup & Config
Time-to-first-conversation. Account creation, Wi-Fi pairing, account linking and onboarding tutorials.
40%
of category
App & Voice
Companion app polish, plus voice-activation reliability and supported languages.
35%
of category
Software Updates
Frequency and quality of updates, plus the manufacturer's track record on long-term support (servers staying online).
25%
of category

4. Build Quality

15% of final score

Materials, finish, and battery life — companion robots live on a desk for years.

Build & Durability
Plastic / metal quality, motor longevity for animated joints, and resistance to dust and accidental drops.
50%
of category
Battery Life
Active runtime per charge and standby time. Companion robots that need to be docked every couple of hours score lower.
50%
of category

5. Value for Money

15% of final score

Companion robots span a wide price range; capability per dollar matters more here than in industrial categories.

Price / Performance
Personality, AI capability and feature breadth at the robot's price tier.
70%
of category
Market Availability
Where you can buy it new, plus availability of replacement units and accessories.
30%
of category
Robot pets

How a robot pet's overall score is calculated

Robot pets live or die on how lifelike they feel. Behaviour realism gets the heaviest weight (30%), with responsiveness and the rest of the categories filling out the framework. Build quality matters because pets are picked up and dropped, and battery life because pets that "sleep" all day get boring fast.

Behaviour Realism30 %
Responsiveness & AI25 %
Ease of Use15 %
Build Quality15 %
Value for Money15 %

1. Behaviour Realism

30% of final score

Movement quality, expressiveness and personality depth — the three things a person can sense within minutes of unboxing.

Movement Quality
How natural the locomotion looks. Servo precision, gait variety and reaction speed all contribute.
  • 1–3: Stiff, mechanical movement, very few gaits.
  • 4–6: Multiple gaits, occasionally robotic.
  • 7–9: Smooth multi-gait locomotion with playful behaviour.
  • 10: Indistinguishable-from-life-like at a glance, dynamic recovery from stumbles.
40%
of category
Expressiveness
Eyes, ears, tail, posture and sound — how richly the pet conveys mood and reaction.
35%
of category
Personality Depth
Distinct moods and quirks. Whether the pet feels like the same character a month in, with preferences, habits and surprises.
25%
of category

2. Responsiveness & AI

25% of final score

How well the pet reacts to touch, voice and the long-term changes in its environment.

Touch Response
Reaction to petting, scratching, and being picked up — capacitive sensors, accelerometer-based behaviours and animations.
35%
of category
Voice Recognition
Wake-word reliability, name recognition, and the pet's ability to obey simple commands ("come", "sit", "play").
35%
of category
AI Learning & Adapt
Whether the pet adapts to the user over time — face/voice recognition, preferences, and behaviour shifts that make each unit feel unique.
30%
of category

3. Ease of Use

15% of final score

How quickly the pet "wakes up" the first time, and how good the companion app is for daily play.

Setup & Pairing
Out-of-the-box experience, charging, Wi-Fi/Bluetooth pairing and onboarding.
50%
of category
App & Control
App polish, remote-control mode, training tools and personality customisation. Cloud features that may shut down lower this score.
50%
of category

4. Build Quality

15% of final score

Robot pets get picked up, dropped, hugged and rolled — durability and battery life decide whether they stay loved or end up in a drawer.

Build & Durability
Servo lifetime, impact resistance, drop-tolerance and overall fit and finish. Premium pets use metal gears for the most-used joints.
50%
of category
Battery Life
Active playtime per charge and how the pet behaves on a low battery (sleep mode vs. dying mid-play).
50%
of category

5. Value for Money

15% of final score

Robot pets range from $150 toys to $3,000 collectibles, so price relative to capability really matters.

Price / Performance
Behaviour realism, AI features and build quality vs. the pet's price tier.
70%
of category
Market Availability
Where the pet is sold, the state of the second-hand market, and whether spare parts are still available.
30%
of category

Editorial independence

RobotTesters is an independent publication. No manufacturer pays for scores, rankings or featured placements. All scores are assigned by our editorial team based on publicly available specifications, hands-on testing where possible, and cross-referenced technical documentation.

Affiliate links (where present) help fund the site but have zero influence on scores. If you believe a score is incorrect or outdated, please reach out at info@robottesters.com — we welcome corrections.