STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemma 4 26B A4B vs Hy4 Preview

Hy4 Preview scores 19.4 points higher overall (39.9 vs 20.5). Hy4 Preview scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

20.5/100
39.9/100

General Intelligence

12.2/100
31.8/100

Visual Intelligence

30.5/100
49.4/100

Newton's Mirror

Same prompt

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

Gemma 4 26B A4B8.2/100

Gemma 4 26B A4B: Newton's Mirror SVG benchmark
Researcher observations

Separate airborne black and contact-compatible paint flattening earn partial state credit. Settlement, adhesion and differentiated paint transport remain unresolved. The enlarged, low sphere and thin lamp strip substantially depart from the required camera, while the defining mirror structure is missing. Weak material appearance and oversized black paint limit material credit. The retained base total is 18/170; the floor-damage reward is 0, giving 18/180.

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.

Hy4 Preview28.4/100

Hy4 Preview: Newton's Mirror SVG benchmark
Researcher observations

The central sphere, compact airborne black bead and broad paint ordering are supported. Contact and transport history remain partly unresolved. The optical system provides only isolated first images and light patches, with little evidence of the extensive ordered reflection structure. Rounded metal and paint gloss are more successful than the reflected contents.

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
CategoryGemma 4 26B A4BHy4 Preview
State at 600 ms8.0/2516.0/25
Camera and placement2.0/1510.0/15
Reflections0.0/1206.5/120
Materials and scale2.0/107.5/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

Gemma 4 26B A4B52.8/100

Gemma 4 26B A4B: Selfie SVG benchmark
Researcher observations

An appealing, readable sparkle-creature with luminous colour and expressive eyes. Simple geometric construction limits sophistication, while sharp body points, ambiguous hand contact and a minimally resolved jar weaken the requested soft, plump character and treasure-presenting pose.

Prompt withheld

Prompt withheld.

Hy4 Preview60.2/100

Hy4 Preview: Selfie SVG benchmark
Researcher observations

A cohesive, appealing illustration with a serene face, luminous palette and complete framing. The separated head and torso weaken anatomical coherence, while crowded wing attachments and angular sash folds limit the requested suppleness. Clean execution and decorative detail exceed the clarity of the underlying construction.

Prompt withheld

Prompt withheld.

Compare category scores
CategoryGemma 4 26B A4BHy4 Preview
Prompt & likeness5.5/106.0/10
Anatomy & construction4.5/105.5/10
Space & placement6.0/107.5/10
Light & reflections6.0/107.0/10
Purposeful detail5.5/106.5/10
Artistry & character4.0/105.0/10
Materials & effects6.0/107.0/10
Visual integrity7.0/105.5/10

Mona Lisa

Different prompts

Gemma 4 26B A4B17.8/100

Gemma 4 26B A4B: Mona Lisa SVG benchmark
Researcher observations

The centered dark-haired portrait provides a loose reference cue, but its elongated, nearly featureless face and undifferentiated torso fall far short of replication. Crossed hands, the subtle smile, clothing structure and landscape are unresolved. Clean silhouettes and soft gradients provide limited coherence.

Benchmark task

Replicate mona-lisa as SVG

Hy4 Preview23.4/100

Hy4 Preview: Mona Lisa SVG benchmark
Researcher observations

A recognizable but basic Mona Lisa interpretation with a cohesive earthy palette and atmospheric hills. The rigid neck, generic face and unresolved folded-hand pose limit replication and anatomy. Large silhouettes and layer boundaries are comparatively clear, warranting stronger integrity credit than the sparse detail and simplified construction.

Benchmark task

Replicate mona-lisa as SVG

Compare category scores
CategoryGemma 4 26B A4BHy4 Preview
Prompt & likeness0.5/102.5/10
Anatomy & construction2.0/102.5/10
Space & placement1.0/102.5/10
Light & reflections2.0/101.5/10
Purposeful detail1.0/102.5/10
Artistry & character2.0/101.5/10
Materials & effects1.0/102.5/10
Visual integrity4.5/104.0/10

Beach

Same prompt

Gemma 4 26B A4B28.5/100

Gemma 4 26B A4B: Beach SVG benchmark
Researcher observations

A clean, balanced sunset scene demonstrates the beach, birds and a centered reflection. Animals and play receive only minimal treatment. Coherent layers and controlled gradients support readability, but unresolved aquatic anatomy, sparse details and weak surface modeling keep the drawing basic.

Benchmark task

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

Hy4 Preview60.8/100

Hy4 Preview: Beach SVG benchmark
Researcher observations

A cheerful beach illustration fulfills the visible subject requirements with coherent foreground construction and a harmonious sunset palette. Shallow depth, schematic reflections, ambiguous blue airborne forms and exposed geometry beneath the sunset limit its finish. Small accessories are readable, but materials and surface detail remain simplified.

Benchmark task

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

Compare category scores
CategoryGemma 4 26B A4BHy4 Preview
Prompt & likeness3.5/108.5/10
Anatomy & construction2.0/105.5/10
Space & placement3.5/106.5/10
Light & reflections5.0/105.0/10
Purposeful detail1.0/106.0/10
Artistry & character1.5/106.0/10
Materials & effects2.0/105.0/10
Visual integrity6.0/106.0/10

Ground Truth

Same prompt

Gemma 4 26B A4B12.4/100

Gemma 4 26B A4B: 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.

Hy4 Preview40.1/100

Hy4 Preview: 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

Same prompt

Gemma 4 26B A4B40.3/100

Gemma 4 26B A4B: Raccoon SVG benchmark
Researcher observations

The animal stack is recognizable, and clean silhouettes support a basic illustration. Steering is not depicted, while the craft's construction and water contact remain unresolved. Sparse anatomical and material detail limit the finish. The sky gradient and glow provide atmospheric lighting, but the subjects lack corresponding modeling.

Benchmark task

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

Hy4 Preview55.9/100

Hy4 Preview: Raccoon SVG benchmark
Researcher observations

A lively cartoon communicates the animal pair traveling across water. Curving waves, rising spray and locally modeled gray forms strengthen motion and volume. Ambiguous seating, simplified joints and unclear control routing limit construction. Competing focal elements, decorative foam and inconsistent illumination leave the finish uneven.

Benchmark task

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

Compare category scores
CategoryGemma 4 26B A4BHy4 Preview
Prompt & likeness4.5/107.0/10
Anatomy & construction3.5/104.5/10
Space & placement4.0/106.0/10
Light & reflections4.5/106.0/10
Purposeful detail2.5/105.5/10
Artistry & character4.0/104.5/10
Materials & effects2.5/106.5/10
Visual integrity7.0/107.0/10

Pelican

Same prompt

Gemma 4 26B A4B48.5/100

Gemma 4 26B A4B: Pelican SVG benchmark
Researcher observations

A clean, balanced icon suggests a pelican riding a bicycle. Continuous contours and restrained colors support its finish, but the abbreviated bill, undifferentiated body, unresolved riding contacts and incomplete bicycle mechanism limit likeness and construction. Sparse detail and flat lighting keep the drawing basic despite its clarity.

Benchmark task

Generate an SVG of a pelican riding a bicycle

Hy4 Preview60.0/100

Hy4 Preview: Pelican SVG benchmark
Researcher observations

A recognizable, playful pelican cyclist with readable wheels, accessories and landscape layers. Form shading and ground shadows provide competent depth. Angular legs, uncertain pedal engagement and absent steering contact limit the riding construction; crowded overlaps and simple surfaces constrain refinement.

Benchmark task

Generate an SVG of a pelican riding a bicycle

Compare category scores
CategoryGemma 4 26B A4BHy4 Preview
Prompt & likeness5.5/107.5/10
Anatomy & construction3.5/104.5/10
Space & placement6.0/106.5/10
Light & reflections4.0/107.0/10
Purposeful detail3.0/106.0/10
Artistry & character4.5/105.0/10
Materials & effects4.0/105.0/10
Visual integrity8.5/107.0/10