STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Gemma 4 26B A4B vs GLM-5.3-Flash (Ox Alpha)

GLM-5.3-Flash (Ox Alpha) scores 32.9 points higher overall (53.4 vs 20.5). Ox Alpha scores higher on Ground Truth.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

20.5/100
53.4/100

General Intelligence

12.2/100
48.7/100

Visual Intelligence

30.5/100
60.1/100

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.

GLM-5.3-Flash (Ox Alpha)27.4/100

Ox Alpha: Newton's Mirror SVG benchmark
Researcher observations

The setup is recognizable, but the paint interaction remains poorly established and off-center. The first wall and floor images provide coherent placement, scale, silhouette and occlusion cues, with faint lower echoes. Missing receding chains, nested imagery and ordered emitter mappings leave the reflection system heavily simplified. Dull shading does not convincingly depict polished steel or mirrors.

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 A4BGLM-5.3-Flash (Ox Alpha)
State at 600 ms8.0/2512.5/25
Camera and placement2.0/1510.0/15
Reflections0.0/12021.5/120
Materials and scale2.0/103.5/10
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.

GLM-5.3-Flash (Ox Alpha)76.6/100

Ox Alpha: Selfie SVG benchmark
Researcher observations

The expressive emerald face, ivory horns, gold accents and fine veining closely match the brief. Rounded volumes and layered shading create an appealing mascot. Rear hoof placement is cramped, lighting is somewhat inconsistent, and conspicuous white patches behind the muzzle interrupt the finish. Surfaces remain visibly stylized rather than photographic.

Benchmark task

Draw a friendly green bull with a big head, ivory horns and gold details. It lifts one front hoof and wears a gold alpha symbol on its forehead. Make its rounded body look like polished stone.

Compare category scores
CategoryGemma 4 26B A4BGLM-5.3-Flash (Ox Alpha)
Prompt & likeness5.5/108.5/10
Anatomy & construction4.5/107.5/10
Space & placement6.0/107.5/10
Light & reflections6.0/108.0/10
Purposeful detail5.5/107.5/10
Artistry & character4.0/107.5/10
Materials & effects6.0/107.5/10
Visual integrity7.0/107.0/10

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

GLM-5.3-Flash (Ox Alpha)49.5/100

Ox Alpha: Mona Lisa SVG benchmark
Researcher observations

The crossed arms, green dress and hazy landscape clearly evoke Mona Lisa. Replication is limited by the frontal pose, oversized eyes, elongated face and pronounced lips. Overlapping finger strips lack convincing knuckles and palm volume. The balanced framing and soft shading provide cohesion, but simplified anatomy, repetitive folds and blurred scenery keep the portrait basic.

Benchmark task

Generate an SVG of mona-lisa

Compare category scores
CategoryGemma 4 26B A4BGLM-5.3-Flash (Ox Alpha)
Prompt & likeness0.5/104.5/10
Anatomy & construction2.0/104.5/10
Space & placement1.0/106.0/10
Light & reflections2.0/106.0/10
Purposeful detail1.0/105.0/10
Artistry & character2.0/105.0/10
Materials & effects1.0/105.5/10
Visual integrity4.5/104.0/10

Beach

Different prompts

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

GLM-5.3-Flash (Ox Alpha)77.7/100

Ox Alpha: Beach SVG benchmark
Researcher observations

Framing palms, a vivid sunset palette and balanced kite and umbrella create an appealing beach illustration. Layered water and shoreline give the scene depth, while aligned reflections reinforce the sunset. Small accessories add character and reward inspection. Figures and animals remain schematic, some overlaps are difficult to read, and simplified shadows and flat surfaces limit physical richness.

Benchmark task

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

Compare category scores
CategoryGemma 4 26B A4BGLM-5.3-Flash (Ox Alpha)
Prompt & likeness3.5/108.0/10
Anatomy & construction2.0/107.0/10
Space & placement3.5/108.0/10
Light & reflections5.0/108.0/10
Purposeful detail1.0/108.0/10
Artistry & character1.5/108.5/10
Materials & effects2.0/106.5/10
Visual integrity6.0/108.0/10

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.

GLM-5.3-Flash (Ox Alpha)64.3/100

Ox Alpha: 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

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

Compare category scores
CategoryGemma 4 26B A4BGLM-5.3-Flash (Ox Alpha)
Prompt & likeness4.5/10—
Anatomy & construction3.5/10—
Space & placement4.0/10—
Light & reflections4.5/10—
Purposeful detail2.5/10—
Artistry & character4.0/10—
Materials & effects2.5/10—
Visual integrity7.0/10—

Pelican

Different prompts

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

GLM-5.3-Flash (Ox Alpha)75.8/100

Ox Alpha: Pelican SVG benchmark
Researcher observations

The pelican, bicycle and seaside setting form a clear, appealing illustration. Circular wheels, readable frame tubes and clean silhouettes support the action. The legs connect to the body, but the far foot's pedal contact and wing-to-handlebar junction are cramped. Simple shading, uniform wave marks and limited surface texture keep the rendering relatively flat.

Benchmark task

Generate a still SVG of a pelican riding a bicycle

Compare category scores
CategoryGemma 4 26B A4BGLM-5.3-Flash (Ox Alpha)
Prompt & likeness5.5/108.5/10
Anatomy & construction3.5/107.5/10
Space & placement6.0/107.5/10
Light & reflections4.0/106.5/10
Purposeful detail3.0/107.0/10
Artistry & character4.5/108.0/10
Materials & effects4.0/106.5/10
Visual integrity8.5/108.0/10