Cyborg Index · July 2026

Figure 03 vs UBTech Walker S

Both humanoids read on the same 8 axes and 40 sub-axes, using the published Index scores. Every difference below carries the public evidence behind it, and sub-axes with no public evidence count as 0 rather than being skipped.

Overall standing

Capability score · 0–5 over 40 sub-axes

Figure 03

Figure AI

1.13of 5

Rank

Coverage

24/40

Proof

0.08

UBTech Walker S

UBTech

1.70of 5

Rank

Coverage

29/40

Proof

0.13

The short answer

UBTech Walker S scores 0.57 higher than Figure 03, but that lead rests mostly on vendor claims and demos.

Only 8% of UBTech Walker S's score is carried by independently verified material — the rest is claimed or shown in demos. Figure 03 has more unscored ground than the gap between them, so this could change next month.

Where Figure 03 is ahead

Learning+1.00Rests on claims and demos
Safety+0.20Rests on claims and demos

Where UBTech Walker S is ahead

Deployment+1.40Rests on claims and demos
Locomotion+1.00Rests on claims and demos
Autonomy+1.00Rests on claims and demos
HRI+1.00Rests on claims and demos

What would change it

10 sub-axes on the trailing side have no public evidence yet. If all of them scored full marks they would be worth 1.25 — against a gap of 0.57.

Locomotion · Uneven terrainup to +0.125
Locomotion · Stairsup to +0.125
Locomotion · Flat ground walkingup to +0.125
Perception · Spatial memoryup to +0.125
HRI · Intent recognitionup to +0.125

There is more unscored ground than there is gap, so this result could turn over after the next research month.

How much we know

66%of sub-axes covered

We have public evidence for 66% of the 40 sub-axes across these two.

Figure 03 · 60%

UBTech Walker S · 73%

The shape of each score

Figure 031.13

24/40 sub-axes have evidence

Faint outline = UBTech Walker S

UBTech Walker S1.70

29/40 sub-axes have evidence

Faint outline = Figure 03

Reading the wheels — clockwise from the top

1 Locomotion
2 Manipulation
3 Perception
4 Autonomy
5 Learning
6 HRI
7 Deployment
8 Safety

Each wheel has 40 spokes — five per axis. A longer spoke is a higher score, and the dashed rings mark 1 to 4. Hover or tab onto any spoke to read the axis, the sub-axis and the exact value. A missing spoke means there is no public evidence for that sub-axis yet, which is not the same as scoring zero. The faint outline on each wheel is the other humanoid, drawn on the same scale.

Every axis, every sub-axis

Deployment1.40 Locomotion1.00 Autonomy1.00 Learning1.00 HRI1.00 Manipulation0.80 Perception0.60 Safety0.20

Figure 03UBTech Walker S

Shared 0–5 track · widest gap first

Deployment

1.20 / 2.60► 1.40

Rests on claims and demosEvidenced cells · 4/5 vs 4/5

Named pilots

2.00 / 3.00► 1.00

Field hours

1.00 / —◄ 1.00

Customer diversity

1.00 / 4.00► 3.00

Supportability

2.00 / 2.00

Commercial posture

— / 4.00► 4.00

Locomotion

0.60 / 1.60► 1.00

Rests on claims and demosEvidenced cells · 1/5 vs 4/5

Flat ground walking

— / 2.00► 2.00

Uneven terrain

— / 2.00► 2.00

Stairs

— / 2.00► 2.00

Disturbance recovery

— / —

Speed endurance

3.00 / 2.00◄ 1.00

Autonomy

1.00 / 2.00► 1.00

Rests on claims and demosEvidenced cells · 2/5 vs 5/5

Unattended operation

— / 1.00► 1.00

Task horizon

3.00 / 3.00

Generalization

— / 2.00► 2.00

Instruction following

2.00 / 2.00

Recovery from failure

— / 2.00► 2.00

Learning

1.40 / 0.40◄ 1.00

Rests on claims and demosEvidenced cells · 4/5 vs 1/5

Imitation learning

1.00 / —◄ 1.00

Sim to real

2.00 / —◄ 2.00

Foundation policy

2.00 / 2.00

Data flywheel

— / —

Transfer fine tune

2.00 / —◄ 2.00

HRI

1.80 / 2.80► 1.00

Rests on claims and demosEvidenced cells · 4/5 vs 5/5

Speech io

2.00 / 2.00

Nl instruction

2.00 / 2.00

Intent recognition

— / 2.00► 2.00

Safe proximity

3.00 / 4.00► 1.00

Social presentation

2.00 / 4.00► 2.00

Manipulation

1.00 / 1.80► 0.80

Rests on claims and demosEvidenced cells · 3/5 vs 4/5

Grasp variety

2.00 / 2.00

Bimanual

1.00 / 3.00► 2.00

Force control

2.00 / 2.00

In hand reorient

— / —

Tool use

— / 2.00► 2.00

Perception

1.00 / 1.60► 0.60

Rests on claims and demosEvidenced cells · 3/5 vs 4/5

Sensor stack

2.00 / 2.00

Scene understanding

1.00 / 2.00► 1.00

Spatial memory

— / 2.00► 2.00

Object permanence

— / —

Semantic world model

2.00 / 2.00

Safety

1.00 / 0.80◄ 0.20

Rests on claims and demosEvidenced cells · 3/5 vs 2/5

Functional safety

2.00 / 2.00

Certifications

2.00 / —◄ 2.00

E stop arch

— / —

Incident transparency

— / —

Force impact limits

1.00 / 2.00► 1.00

Segment length and thickness are the gapNo public evidence yet

Which is better for what

Each row is decided by the axes that matter for that kind of work, read off the same Capability scores as the ranking. Rows only appear where both humanoids have enough public record to answer.

Manufacturing and warehouse work

Named pilots and field hours, backed by what the hands can actually do.

UBTech Walker S

UBTech Walker S scores higher on Deployment and Manipulation — 2.33 against 1.13 for Figure 03.

Running without a human in the loop

Unattended operation and task horizon, backed by what the robot can perceive.

UBTech Walker S

UBTech Walker S scores higher on Autonomy and Perception — 1.87 against 1.00 for Figure 03.

Working alongside people

Functional safety and certification, plus how it reads and answers people.

UBTech Walker S

UBTech Walker S scores higher on Safety and HRI — 1.47 against 1.27 for Figure 03.

Picking up new tasks

Imitation learning, transfer and generalisation across tasks.

Figure 03

Figure 03 scores higher on Learning and Autonomy — 1.27 against 0.93 for UBTech Walker S.

Research and developer use

How much of the stack is documented and reproducible.

Figure 03

Figure 03 scores higher on Learning and Perception — 1.27 against 0.80 for UBTech Walker S.

How solid the record is on each side

Figure 03

Sub-axes on the record: 24 of 40 · 60%
Carried by verified material: 7%
Rests on claims and demos: 1.04

Best documented — Manipulation, Perception, Learning, HRI, Deployment, Safety

Nothing on the record — every axis has at least one read

UBTech Walker S

Sub-axes on the record: 29 of 40 · 73%
Carried by verified material: 8%
Rests on claims and demos: 1.57

Best documented — Locomotion, Manipulation, Perception, Autonomy, HRI, Deployment

Nothing on the record — every axis has at least one read

What this comparison cannot settle

Neither humanoid has a public read on 6 of the 40 sub-axes, so those cannot be compared at all.
15 sub-axes are read on only one side. A one-sided cell is undecided, not a zero for the silent side.
Most of Figure 03's score rests on vendor statements and demo footage rather than independently verified material (7% carried by verified evidence).
Most of UBTech Walker S's score rests on vendor statements and demo footage rather than independently verified material (8% carried by verified evidence).
Demonstrations happen in different environments and product revisions are not always equivalent, so like-for-like uptime and throughput figures do not exist for most of the field.

Go deeper on either humanoid

Nearby comparisons

All comparisons →