Cyborg Index · July 2026

Boston Dynamics Atlas (electric) vs Figure 03

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.

The public record is still thin on at least one side of this pair, so treat the ordering as provisional rather than settled.

Overall standing

Capability score · 0–5 over 40 sub-axes

Boston Dynamics Atlas (electric)

Boston Dynamics

0.68of 5

Rank

#10

Coverage

14/40

Proof

0.11

Figure 03

Figure AI

1.13of 5

Rank

Coverage

24/40

Proof

0.08

The short answer

Figure 03 scores 0.45 higher than Boston Dynamics Atlas (electric), but that lead rests mostly on vendor claims and demos.

Only 7% of Figure 03's score is carried by independently verified material — the rest is claimed or shown in demos. Boston Dynamics Atlas (electric) has more unscored ground than the gap between them, so this could change next month.

Where Boston Dynamics Atlas (electric) is ahead

Locomotion+0.40Rests on claims and demos
Manipulation+0.40Rests on claims and demos

Where Figure 03 is ahead

HRI+1.40Rests on claims and demos
Learning+1.00Rests on claims and demos
Autonomy+0.80Rests on claims and demos
Perception+0.60Rests on claims and demos

What would change it

13 sub-axes on the trailing side have no public evidence yet. If all of them scored full marks they would be worth 1.63 — against a gap of 0.45.

Learning · Transfer fine tuneup to +0.125
Perception · Semantic world modelup to +0.125
Autonomy · Instruction followingup to +0.125
Learning · Foundation policyup to +0.125
HRI · Nl instructionup 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

48%of sub-axes covered

We have public evidence for 48% of the 40 sub-axes across these two. Treat this as an early read.

Boston Dynamics Atlas (electric) · 35%

Figure 03 · 60%

Early read

The shape of each score

Boston Dynamics Atlas (electric)0.68

14/40 sub-axes have evidence

Faint outline = Figure 03

Figure 031.13

24/40 sub-axes have evidence

Faint outline = Boston Dynamics Atlas (electric)

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

HRI1.40 Learning1.00 Autonomy0.80 Perception0.60 Safety0.60 Locomotion0.40 Manipulation0.40 Deploymentlevel

Boston Dynamics Atlas (electric)Figure 03

Shared 0–5 track · widest gap first

HRI

0.40 / 1.80► 1.40

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

Speech io

— / 2.00► 2.00

Nl instruction

— / 2.00► 2.00

Intent recognition

— / —

Safe proximity

2.00 / 3.00► 1.00

Social presentation

— / 2.00► 2.00

Learning

0.40 / 1.40► 1.00

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

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

Autonomy

0.20 / 1.00► 0.80

Rests on claims and demosEvidenced cells · 1/5 vs 2/5

Unattended operation

1.00 / —◄ 1.00

Task horizon

— / 3.00► 3.00

Generalization

— / —

Instruction following

— / 2.00► 2.00

Recovery from failure

— / —

Perception

0.40 / 1.00► 0.60

Rests on claims and demosEvidenced cells · 1/5 vs 3/5

Sensor stack

2.00 / 2.00

Scene understanding

— / 1.00► 1.00

Spatial memory

— / —

Object permanence

— / —

Semantic world model

— / 2.00► 2.00

Safety

0.40 / 1.00► 0.60

Rests on claims and demosEvidenced cells · 1/5 vs 3/5

Functional safety

2.00 / 2.00

Certifications

— / 2.00► 2.00

E stop arch

— / —

Incident transparency

— / —

Force impact limits

— / 1.00► 1.00

Locomotion

1.00 / 0.60◄ 0.40

Rests on claims and demosEvidenced cells · 2/5 vs 1/5

Flat ground walking

3.00 / —◄ 3.00

Uneven terrain

— / —

Stairs

— / —

Disturbance recovery

— / —

Speed endurance

2.00 / 3.00► 1.00

Manipulation

1.40 / 1.00◄ 0.40

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

Grasp variety

2.00 / 2.00

Bimanual

3.00 / 1.00◄ 2.00

Force control

2.00 / 2.00

In hand reorient

— / —

Tool use

— / —

Deployment

1.20 / 1.20

Not enough public record yetEvidenced cells · 4/5 vs 4/5

Named pilots

2.00 / 2.00

Field hours

— / 1.00► 1.00

Customer diversity

1.00 / 1.00

Supportability

2.00 / 2.00

Commercial posture

1.00 / —◄ 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.

Boston Dynamics Atlas (electric)

Boston Dynamics Atlas (electric) scores higher on Deployment and Manipulation — 1.27 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.

Figure 03

Figure 03 scores higher on Autonomy and Perception — 1.00 against 0.27 for Boston Dynamics Atlas (electric).

Working alongside people

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

Figure 03

Figure 03 scores higher on Safety and HRI — 1.27 against 0.40 for Boston Dynamics Atlas (electric).

Picking up new tasks

Imitation learning, transfer and generalisation across tasks.

Figure 03

Figure 03 scores higher on Learning and Autonomy — 1.27 against 0.33 for Boston Dynamics Atlas (electric).

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 0.40 for Boston Dynamics Atlas (electric).

How solid the record is on each side

Boston Dynamics Atlas (electric)

Sub-axes on the record: 14 of 40 · 35%
Carried by verified material: 16%
Rests on claims and demos: 0.57

Best documented — Manipulation, Deployment

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

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

What this comparison cannot settle

Neither humanoid has a public read on 13 of the 40 sub-axes, so those cannot be compared at all.
16 sub-axes are read on only one side. A one-sided cell is undecided, not a zero for the silent side.
Public evidence covers 48% of the sub-axes across the two. Treat the overall ordering as an early read.
Most of Boston Dynamics Atlas (electric)'s score rests on vendor statements and demo footage rather than independently verified material (16% carried by verified evidence).
Most of Figure 03's score rests on vendor statements and demo footage rather than independently verified material (7% 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 →

Cyborg IndexJuly 2026 editionCapability scoremethodology