STEALTHMARK · HEAD TO HEAD

All comparisons ↗

DeepSeek V4 Pro 0813 vs Kolibri 1

DeepSeek V4 Pro 0813 scores 24.4 points higher overall (37.4 vs 13.0). DeepSeek V4 Pro 0813 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

37.4/100
13.0/100

General Intelligence

33.7/100
12.1/100

Visual Intelligence

41.8/100
14.2/100

Newton's Mirror

Same prompt

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

DeepSeek V4 Pro 081338.3/100

DeepSeek V4 Pro 0813: Newton's Mirror SVG benchmark
Researcher observations

The central sphere and gross paint state are coherent. Reduced circular side images and paired overhead quadrilaterals offer limited, spatially organized reflection cues, but the floor-sphere image, receding mirror-room structure, outer chains, nested imagery and curved emitter mappings are largely missing or invalid.

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.

Kolibri 19.9/100

Kolibri 1: Newton's Mirror SVG benchmark
Researcher observations

A segmented gray perimeter surrounds a black field containing one large, low-positioned gray sphere and two small colored circles. Rounded volume and restrained paint scale earn partial material credit. The image does not demonstrate the required optical structure, while paint history, airborne black and settled support remain largely unresolved.

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
CategoryDeepSeek V4 Pro 0813Kolibri 1
State at 600 ms25.0/258.5/25
Camera and placement15.0/151.5/15
Reflections11.0/1200.0/120
Materials and scale8.0/103.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

DeepSeek V4 Pro 081342.4/100

DeepSeek V4 Pro 0813: Selfie SVG benchmark
Researcher observations

The whale’s warm eye, lavender assistant and tilted shell convey appealing character. However, the shrimp and reciprocal inspection are unresolved, the large bubble and upper tail are cropped, and the flipper’s grip is unclear. Broad competing color fields and conspicuous stepped edges weaken the flowing composition. Gradients suggest volume, but lighting and translucent materials remain uneven.

Simplified prompt

Draw a curious blue whale examining a tiny shrimp through a bubble magnifying glass. The shrimp looks back through its own smaller bubble lens. An octopus assistant sits on the whale's head while rising bubbles lift a little seaweed wig above it.

The exact prompt is held back to prevent benchmaxxing.

Kolibri 122.9/100

Kolibri 1: Selfie SVG benchmark
Researcher observations

A restrained ivory, teal and green palette gives the image simple graphic coherence. Execution remains rudimentary: detached oval wings, ambiguous central anatomy and unclear feeding contact prevent a convincing hummingbird scene. The requested feather structure, botanical detail, lighting and enclosing arch are largely unresolved.

Prompt withheld

The exact prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryDeepSeek V4 Pro 0813Kolibri 1
Prompt & likeness3.0/102.5/10
Anatomy & construction5.0/102.0/10
Space & placement4.0/103.0/10
Light & reflections5.5/102.0/10
Purposeful detail5.5/101.5/10
Artistry & character2.5/101.5/10
Materials & effects5.0/102.0/10
Visual integrity3.0/105.5/10

Mona Lisa

Same prompt

DeepSeek V4 Pro 081316.9/100

DeepSeek V4 Pro 0813: Mona Lisa SVG benchmark
Researcher observations

Dark hair, a restrained smile and a hazy landscape make the reference recognizable. Severe construction problems dominate: oversized looping sleeves surround a background-colored opening, and the crossed hands lack coherent wrist and forearm connections. Rigid symmetry and elongated facial proportions weaken expression. Soft skin gradients and clean contours provide limited finish.

Exact prompt

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

Kolibri 13.3/100

Kolibri 1: Mona Lisa SVG benchmark
Researcher observations

The candidate offers a clean, highly simplified frontal portrait with warm skin and dark hair. Its oversized oval face, schematic features and unresolved body provide little Mona Lisa likeness. Missing crossed hands, clothing detail and landscape remove essential parts of the original composition; smooth gradients supply only limited volume.

Exact prompt

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

Compare category scores
CategoryDeepSeek V4 Pro 0813Kolibri 1
Prompt & likeness2.0/100.5/10
Anatomy & construction0.5/100.5/10
Space & placement2.0/100.0/10
Light & reflections2.0/100.0/10
Purposeful detail2.0/100.0/10
Artistry & character3.0/100.5/10
Materials & effects1.5/100.5/10
Visual integrity1.0/100.5/10

Beach

Same prompt

DeepSeek V4 Pro 081345.1/100

DeepSeek V4 Pro 0813: Beach SVG benchmark
Researcher observations

The glowing sunset, framing palms and layered shoreline create a coherent beach scene with animals, birds and playful accessories. The airborne blue animal has unclear anatomy, while flat foliage, weak ground contact and broad oval reflections limit depth and finish. The image is appealing but visibly simplified.

Exact prompt

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

Kolibri 112.9/100

Kolibri 1: Beach SVG benchmark
Researcher observations

A recognizable sunset beach has an appealing purple-orange gradient and clean geometric edges. Birds and animals remain unresolved, terrain obscures the relationship between shore and water, and reflections are absent. Sparse detail, flat materials and limited activity keep the drawing elementary despite its tidy rendering.

Exact prompt

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

Compare category scores
CategoryDeepSeek V4 Pro 0813Kolibri 1
Prompt & likeness6.5/102.5/10
Anatomy & construction3.5/100.5/10
Space & placement5.5/103.0/10
Light & reflections6.0/101.0/10
Purposeful detail3.5/100.5/10
Artistry & character3.0/101.0/10
Materials & effects5.5/100.5/10
Visual integrity5.0/103.0/10

Ground Truth

Same prompt

DeepSeek V4 Pro 081338.3/100

DeepSeek V4 Pro 0813: 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.

Kolibri 120.7/100

Kolibri 1: 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

Same prompt

DeepSeek V4 Pro 081354.0/100

DeepSeek V4 Pro 0813: Raccoon SVG benchmark
Researcher observations

The masked raccoon riding the steering dog is readily recognizable, with expressive faces and energetic diagonal movement. The oversized tail dominates the composition, limb connections are difficult to trace, and the jet ski has little structural depth. Blurred spray and a heavy oval shadow weaken water contact, while the glowing sun produces little corresponding illumination.

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

Kolibri 110.0/100

Kolibri 1: Raccoon SVG benchmark
Researcher observations

Clean shapes and a readable coral platform provide basic graphic clarity, but the animal construction remains fragmented. A recognizable raccoon riding the dog's back, connected steering and convincing water contact are not demonstrated. Sparse detail, flat subjects and absent movement effects support retaining the baseline category assessments.

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
CategoryDeepSeek V4 Pro 0813Kolibri 1
Prompt & likeness7.5/101.5/10
Anatomy & construction5.0/101.0/10
Space & placement5.5/101.0/10
Light & reflections4.5/100.0/10
Purposeful detail6.0/100.5/10
Artistry & character5.0/100.5/10
Materials & effects5.0/100.5/10
Visual integrity4.5/103.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for DeepSeek V4 Pro 0813 and Kolibri 1.

DeepSeek V4 Pro 081372.8/100

DeepSeek V4 Pro 0813: Pelican SVG benchmark
Researcher observations

A clearly recognizable pelican cycles through a balanced, expressive illustration. The sweeping bill, shaded plumage and carefully drawn wheels give it character. Mechanical construction is weaker: the chain loop sits below the crank, and foot-to-pedal and wing-to-handlebar contact are ambiguous. Smooth gradients provide volume, but the scene remains visibly stylized.

Exact prompt

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

Kolibri 135.3/100

Kolibri 1: Pelican SVG benchmark
Researcher observations

Clean shapes and aligned wheels establish a readable schematic scene. Pelican likeness, riding support and bicycle mechanics remain substantially unresolved. Sparse detail and flat surfaces limit expression and volume. Strong edge and fill integrity is a separate success and does not repair the construction.

Exact prompt

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

Compare category scores
CategoryDeepSeek V4 Pro 0813Kolibri 1
Prompt & likeness8.5/103.5/10
Anatomy & construction6.0/102.0/10
Space & placement7.0/104.0/10
Light & reflections7.0/103.0/10
Purposeful detail7.5/102.5/10
Artistry & character8.0/103.0/10
Materials & effects7.0/103.0/10
Visual integrity7.5/108.5/10