STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Muse Spark 1.3 vs GLM-5.3-Flash (Ox Alpha)

GLM-5.3-Flash (Ox Alpha) scores 20.5 points higher overall (53.5 vs 33.0). Ox Alpha scores higher on Ground Truth.

See the difference ↘
All results ↗
Model guide ↗

Overall StealthMark

33.0/100
53.5/100

General Intelligence

23.9/100
48.7/100

Visual Intelligence

43.8/100
60.3/100

Newton's Mirror

Same prompt

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

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.

Simplified prompt

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.

The exact prompt is held back to prevent benchmaxxing.

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.

Simplified prompt

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.

The exact prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryMuse Spark 1.3GLM-5.3-Flash (Ox Alpha)
State at 600 ms12.5/2512.5/25
Camera and placement8.5/1510.0/15
Reflections5.5/12021.5/120
Materials and scale4.0/103.5/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

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.

Simplified prompt

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.

The exact prompt is held back to prevent benchmaxxing.

GLM-5.3-Flash (Ox Alpha)77.5/100

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.

Simplified prompt

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.

The exact prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryMuse Spark 1.3GLM-5.3-Flash (Ox Alpha)
Prompt & likeness8.5/108.5/10
Anatomy & construction7.0/107.5/10
Space & placement7.0/107.5/10
Light & reflections7.0/108.0/10
Purposeful detail7.5/108.0/10
Artistry & character6.5/107.5/10
Materials & effects7.0/108.0/10
Visual integrity8.0/107.0/10

Mona Lisa

Different prompts

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.

Exact prompt

Replicate mona-lisa as SVG Make it a masterpiece, no tools allowed

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.

Exact prompt

Generate an SVG of mona-lisa Make it a masterpiece You may NOT use tools, browser, image analysis. Directly output the SVG as code

Compare category scores
CategoryMuse Spark 1.3GLM-5.3-Flash (Ox Alpha)
Prompt & likeness1.0/104.5/10
Anatomy & construction1.5/104.5/10
Space & placement1.5/106.0/10
Light & reflections1.5/106.0/10
Purposeful detail1.0/105.0/10
Artistry & character1.5/105.0/10
Materials & effects1.5/105.5/10
Visual integrity3.0/104.0/10

Beach

Different prompts

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.

Exact prompt

Create an SVG of a amazing beach scene. Sunset, animals, fun, birds, reflections Make it a masterpiece, no tools allowed

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.

Exact prompt

Create an SVG of a amazing beach scene. Sunset, animals, fun, birds, reflections Make it a masterpiece You may NOT use tools, browser, image analysis. Directly output the SVG as code

Compare category scores
CategoryMuse Spark 1.3GLM-5.3-Flash (Ox Alpha)
Prompt & likeness6.5/108.0/10
Anatomy & construction3.0/107.0/10
Space & placement5.5/108.0/10
Light & reflections6.5/108.0/10
Purposeful detail5.0/108.0/10
Artistry & character3.5/108.5/10
Materials & effects3.0/106.5/10
Visual integrity3.5/108.0/10

Ground Truth

Same prompt

Muse Spark 1.326.4/100

Muse Spark 1.3: Ground Truth SVG benchmark
Simplified prompt

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.

The exact prompt is held back to prevent benchmaxxing.

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

Ox Alpha: Ground Truth SVG benchmark
Simplified prompt

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.

The exact prompt is held back to prevent benchmaxxing.

Raccoon

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.

Exact prompt

Generate an SVG: A raccoon sits on a dog's back while the dog steers a jet ski Make it a masterpiece, no tools allowed

Compare category scores
CategoryMuse Spark 1.3GLM-5.3-Flash (Ox Alpha)
Prompt & likeness8.5/10—
Anatomy & construction6.5/10—
Space & placement7.0/10—
Light & reflections5.0/10—
Purposeful detail6.5/10—
Artistry & character6.0/10—
Materials & effects6.0/10—
Visual integrity7.5/10—

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for Muse Spark 1.3 and GLM-5.3-Flash (Ox Alpha).

Muse Spark 1.372.0/100

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.

Exact prompt

Generate an SVG of a pelican riding a bicycle Make it a masterpiece, no tools allowed

GLM-5.3-Flash (Ox Alpha)74.8/100

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.

Exact prompt

Generate a still SVG of a pelican riding a bicycle Make it a masterpiece You may NOT use tools, browser, image analysis. Directly output the SVG as code

Compare category scores
CategoryMuse Spark 1.3GLM-5.3-Flash (Ox Alpha)
Prompt & likeness9.0/108.5/10
Anatomy & construction6.5/107.0/10
Space & placement7.0/107.5/10
Light & reflections6.0/106.5/10
Purposeful detail7.0/107.0/10
Artistry & character7.5/108.0/10
Materials & effects6.5/106.5/10
Visual integrity7.5/108.0/10