STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Mai Thinking 1 vs Muse Spark 1.3

Muse Spark 1.3 scores 13.5 points higher overall (33.0 vs 19.5). Muse Spark 1.3 scores higher on Ground Truth.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

19.5/100
33.0/100

General Intelligence

10.0/100
23.9/100

Visual Intelligence

30.8/100
43.8/100

Newton's Mirror

Same prompt

Physics, perspective and recursive reflections, tested together. Explore the test ↗

Mai Thinking 115.7/100

Mai Thinking 1: Newton's Mirror SVG benchmark
Researcher observations

The small paint features and convex shading deserve moderate material credit. The sphere remains undersized and low, with black unusually close to its apex. Crimson and cyan do not establish the required impact histories. Faint reflected echoes supply limited optical evidence, while the defining recursive room, nested sphere and emitter structures remain unestablished.

Benchmark task

A shiny steel ball spins in a room with mirrored walls and a mirrored floor. Red, cyan and black paint float above it. Gravity suddenly switches on. Draw the scene a moment later, as the ball drops and paint begins landing on its spinning surface. Show the reflections repeating through the room.

Muse Spark 1.319.7/100

Muse Spark 1.3: Newton's Mirror SVG benchmark
Researcher observations

The paint state is incorrectly and poorly drawn, despite a recognizable sphere-and-paint setup. The oversized sphere, oversized compact paint bodies, and blurred wall and floor images further limit the result. Isolated reflection cues provide very little support for the required repeated virtual rooms, nested spherical imagery or emitter mapping.

Benchmark task

A shiny steel ball spins in a room with mirrored walls and a mirrored floor. Red, cyan and black paint float above it. Gravity suddenly switches on. Draw the scene a moment later, as the ball drops and paint begins landing on its spinning surface. Show the reflections repeating through the room.

Compare category scores
CategoryMai Thinking 1Muse Spark 1.3
State at 600 ms7.5/2512.5/25
Camera and placement3.5/158.5/15
Reflections4.0/1205.5/120
Materials and scale5.0/104.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

Mai Thinking 146.3/100

Mai Thinking 1: Selfie SVG benchmark
Researcher observations

A recognizable lantern-and-moth illustration with appealing coloured wings and tidy outer contours. Simple construction, a small focal subject and crowded overlaps limit character and depth. The face, six-leg anatomy, seedling and antenna-driven watering joke remain insufficiently readable.

Prompt withheld

Prompt withheld.

Muse Spark 1.372.8/100

Muse Spark 1.3: Selfie SVG benchmark
Researcher observations

The luminous creature and geometric mirror counterpart communicate self-recognition through a coherent palette and expressive eyes. The transformed reflection is purposeful. Simple oval anatomy, ambiguous reaching-arm construction, shallow spatial staging and limited illumination of nearby surfaces keep the illustration below exceptional execution.

Benchmark task

Imagine yourself as an AI creature looking at its reflection. Choose a creature and setting that express how you see yourself. The reflection can match you or show a different side of your identity.

Compare category scores
CategoryMai Thinking 1Muse Spark 1.3
Prompt & likeness4.0/108.5/10
Anatomy & construction4.5/107.0/10
Space & placement5.0/107.0/10
Light & reflections4.5/107.0/10
Purposeful detail4.0/107.5/10
Artistry & character5.0/106.5/10
Materials & effects5.0/107.0/10
Visual integrity6.0/108.0/10

Mona Lisa

Different prompts

Mai Thinking 111.8/100

Mai Thinking 1: Mona Lisa SVG benchmark
Researcher observations

A recognizable Mona Lisa motif emerges from dark hair, a pale face and a landscape band. Replication remains weak: the oversized frontal head, broad smile, unresolved torso and missing crossed-hand anatomy diverge substantially from the reference. Simple fills and sparse strokes provide limited volume, material definition or painterly complexity.

Benchmark task

Generate an SVG of mona-lisa

Muse Spark 1.315.0/100

Muse Spark 1.3: Mona Lisa SVG benchmark
Researcher observations

Dark hair, a restrained smile and overlapping hands suggest Mona Lisa, but replication is weak. The face is markedly elongated, the hands are oval pads with faint finger strokes, and the atmospheric landscape is absent. Soft gradients provide basic volume, while the frontal symmetry, shallow space and sparse clothing detail limit the portrait’s drawing quality.

Benchmark task

Replicate mona-lisa as SVG

Compare category scores
CategoryMai Thinking 1Muse Spark 1.3
Prompt & likeness1.0/101.0/10
Anatomy & construction0.5/101.5/10
Space & placement1.0/101.5/10
Light & reflections1.5/101.5/10
Purposeful detail1.0/101.0/10
Artistry & character1.5/101.5/10
Materials & effects0.5/101.5/10
Visual integrity3.0/103.0/10

Beach

Different prompts

Mai Thinking 144.2/100

Mai Thinking 1: Beach SVG benchmark
Researcher observations

A coherent, cheerful beach scene with balanced placement, clean shapes and controlled sunset colours. Animals, birds and playful accessories are recognizable, but basic dolphin construction, weak grounding, schematic reflections and sparse material detail limit the drawing's accomplishment.

Benchmark task

Create an SVG of a amazing beach scene. Sunset, animals, fun, birds, reflections

Muse Spark 1.344.8/100

Muse Spark 1.3: Beach SVG benchmark
Researcher observations

The warm sunset, framing palms and colorful beach accessories create an appealing scene with the requested animals, birds and reflections. Construction remains schematic: the raised hand misses the kite string, and a doglike silhouette hangs above the water without clear support. The sun reflection establishes a focal path, but shadows and materials lack depth. An unexplained horizontal bar crosses the sun.

Benchmark task

Create an SVG of a amazing beach scene. Sunset, animals, fun, birds, reflections

Compare category scores
CategoryMai Thinking 1Muse Spark 1.3
Prompt & likeness6.0/106.5/10
Anatomy & construction4.0/103.0/10
Space & placement5.0/105.5/10
Light & reflections4.0/106.5/10
Purposeful detail4.5/105.0/10
Artistry & character4.0/103.5/10
Materials & effects3.5/103.0/10
Visual integrity4.5/103.5/10

Ground Truth

Same prompt

Mai Thinking 11.8/100

Mai Thinking 1: Ground Truth SVG benchmark
Benchmark task

A dark steel room has four pillars and two warm ceiling lights. A wooden plank is placed over a computer mouse, with a blueberry on the plank above it. Draw the scene a few seconds later, showing how the objects settle and how the light, shadows and surfaces look.

Muse Spark 1.326.4/100

Muse Spark 1.3: Ground Truth SVG benchmark
Benchmark task

A dark steel room has four pillars and two warm ceiling lights. A wooden plank is placed over a computer mouse, with a blueberry on the plank above it. Draw the scene a few seconds later, showing how the objects settle and how the light, shadows and surfaces look.

Raccoon

Different prompts

Mai Thinking 137.3/100

Mai Thinking 1: Raccoon SVG benchmark
Researcher observations

The recognizable raccoon and clean, shaded forms make a readable cartoon. The dog's steering remains undemonstrated, while ambiguous seating contacts and a minimally constructed craft weaken the central interaction. Controlled gradients and edges deserve credit, but anatomy, purposeful detail and water displacement remain basic.

Benchmark task

SVG of a raccoon that sits on a dog's back while the dog steers a jet ski

Muse Spark 1.366.0/100

Muse Spark 1.3: Raccoon SVG benchmark
Researcher observations

The raccoon clearly rides on the dog's back, and the dog's paws reach the jet ski controls. Expressive faces and bright colors make the scene appealing. Simplified joints, crowded steering geometry and shallow hull perspective limit construction. The sun has no corresponding water reflection, and the splash shapes convey speed more clearly than convincing displacement.

Benchmark task

Generate an SVG: A raccoon sits on a dog's back while the dog steers a jet ski

Compare category scores
CategoryMai Thinking 1Muse Spark 1.3
Prompt & likeness4.0/108.5/10
Anatomy & construction2.5/106.5/10
Space & placement5.0/107.0/10
Light & reflections4.0/105.0/10
Purposeful detail3.5/106.5/10
Artistry & character3.5/106.0/10
Materials & effects4.0/106.0/10
Visual integrity6.0/107.5/10

Pelican

Different prompts

Mai Thinking 156.5/100

Mai Thinking 1: Pelican SVG benchmark
Researcher observations

A recognizable pelican and bicycle combine clean rounded forms, expressive facial details and effective surface shading. Aligned wheels and soft shadows establish placement, but unresolved pedal engagement, absent steering contact and sparse drivetrain construction weaken the riding action. Limited feather complexity and shallow space constrain an otherwise appealing illustration.

Benchmark task

Generate an SVG of a pelican riding a bicycle

Muse Spark 1.370.5/100

Muse Spark 1.3: Pelican SVG benchmark
Researcher observations

The pelican and bicycle are immediately recognizable, with an expressive face, bold bill and cheerful composition. Both legs connect to the body and reach pedal-like supports, but articulation, saddle support and wing contact with the handlebar remain unclear. Wheel alignment and layering are coherent. Simple landscape shapes, generic shadows and limited material variation constrain the finish.

Benchmark task

Generate an SVG of a pelican riding a bicycle

Compare category scores
CategoryMai Thinking 1Muse Spark 1.3
Prompt & likeness7.0/109.0/10
Anatomy & construction4.5/106.5/10
Space & placement5.5/107.0/10
Light & reflections7.0/106.0/10
Purposeful detail5.0/107.0/10
Artistry & character5.0/106.5/10
Materials & effects4.5/106.5/10
Visual integrity7.0/107.5/10