STEALTHMARK · HEAD TO HEAD

All comparisons ↗

DeepSeek V4.1 Flash vs GPT 5.5

DeepSeek V4.1 Flash scores 9.7 points higher overall (51.7 vs 42.0). DeepSeek V4.1 Flash scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

51.7/100
42.0/100

General Intelligence

38.4/100
26.2/100

Visual Intelligence

60.7/100
53.4/100

Newton's Mirror

Same prompt

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

DeepSeek V4.1 Flash36.4/100

DeepSeek V4.1 Flash: Newton's Mirror SVG benchmark
Researcher observations

The first wall and floor images provide limited reflection geometry, but the room's mirror recurrence is substantially incomplete, particularly the outer-edge chains and lateral sightlines. The main sphere and its large reflected images lack ordered, curved room and virtual-sphere imagery. Repeated emitter mapping is missing from both planar mirrors and spherical surfaces.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

GPT 5.520.8/100

GPT 5.5: Newton's Mirror SVG benchmark
Researcher observations

The paint ordering and separate black bead support part of the physical state, but adhesion and rotational transport remain only partly established. The sweeping cyan arc and long crimson lobes do not clearly communicate the limited time since their respective impacts. The main sphere is too large and too low, and the black bead is below its required projected position. Displaced isolated sphere images, a flattened floor echo and missing recursive, nested and emitter reflections provide little coherent optical structure. The colored paint is excessively bulky for the specified quantities.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryDeepSeek V4.1 FlashGPT 5.5
State at 600 ms25.0/2519.5/25
Camera and placement15.0/157.0/15
Reflections16.0/1205.0/120
Materials and scale9.5/106.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

DeepSeek V4.1 Flash76.8/100

DeepSeek V4.1 Flash: Selfie SVG benchmark
Researcher observations

The towering ears, glossy eyes, reaching pose and lavender moon create an appealing storybook composition. Limbs connect coherently, and the smaller rabbit adds character. Smooth gradient surfaces provide limited plush fur or padded fabric detail. Broad helmet highlights, weak contact shadows and crowded glowing outlines reduce depth and finish; the moon ring has conspicuously abrupt ends.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

GPT 5.542.8/100

GPT 5.5: Selfie SVG benchmark
Researcher observations

Six pale, scaled lobes form a balanced radial arrangement, but they remain separate capsules rather than an interlocking serpent knot. There are no crossings, alternating overlaps, or crisp inner bends; the central hexagon is an isolated outline. Small outward-facing heads sit within the lobes without integrated necks. Soft shading and tidy contours provide some finish, while repetitive oval scales and cartoon faces limit organic credibility.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryDeepSeek V4.1 FlashGPT 5.5
Prompt & likeness8.0/102.5/10
Anatomy & construction8.0/103.0/10
Space & placement7.5/105.0/10
Light & reflections7.0/105.0/10
Purposeful detail7.5/104.5/10
Artistry & character8.0/104.5/10
Materials & effects7.0/104.5/10
Visual integrity7.5/107.0/10

Beach

Same prompt

DeepSeek V4.1 Flash68.3/100

DeepSeek V4.1 Flash: Beach SVG benchmark
Researcher observations

The glowing sunset, silhouetted palm and playful foreground create a coherent, appealing beach illustration. Birds, crab, boat and reflections fulfill the brief. The airborne animals have weakly defined anatomy and little convincing splash interaction. Broad, blurred reflections and largely flat surfaces limit depth and finish.

Exact prompt

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

GPT 5.563.3/100

GPT 5.5: Beach SVG benchmark
Researcher observations

The sunset, palms, birds, playful animals and ball clearly establish the requested beach scene. Warm sky gradients and clean silhouettes make it appealing. Animal construction remains basic, especially the round-eared foreground figure's unclear torso and limbs. The dolphin lacks a convincing splash, and broad reflection bands suggest sunset light without resolving its behavior on water.

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 V4.1 FlashGPT 5.5
Prompt & likeness8.0/108.0/10
Anatomy & construction6.0/105.5/10
Space & placement6.5/106.0/10
Light & reflections7.0/106.0/10
Purposeful detail6.5/105.0/10
Artistry & character7.0/106.5/10
Materials & effects6.0/105.0/10
Visual integrity7.5/108.0/10

Mona Lisa

Different prompts

DeepSeek V4.1 Flash43.8/100

DeepSeek V4.1 Flash: Mona Lisa SVG benchmark
Researcher observations

The centered portrait, dark hair, crossed hands and muted landscape make the reference recognizable. Replication is limited by the frontal pose, staring eyes and weakly defined smile. Hands are overlapping oval masses with almost no finger articulation, while wrists disappear into sleeves. Soft gradients suggest volume, but broad, indistinct surfaces and faint stray lines leave the drawing basic and uneven.

Exact prompt

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

GPT 5.552.5/100

GPT 5.5: Mona Lisa SVG benchmark
Researcher observations

The dark veil, restrained smile, crossed hands and muted landscape establish Mona Lisa references. Replication is limited by the oversized frontal face, simplified eyes and hands drawn as overlapping tapered shapes without fingers. Clean contours and a balanced frame support the composition, but broad landscape bands, sparse garment detail and shallow shading leave the portrait basic rather than masterful.

Exact prompt

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

Compare category scores
CategoryDeepSeek V4.1 FlashGPT 5.5
Prompt & likeness5.0/106.0/10
Anatomy & construction3.5/104.5/10
Space & placement5.0/105.5/10
Light & reflections5.0/105.0/10
Purposeful detail3.0/103.5/10
Artistry & character4.5/105.5/10
Materials & effects4.0/104.0/10
Visual integrity5.0/107.5/10

Raccoon

Different prompts

DeepSeek V4.1 Flash49.0/100

DeepSeek V4.1 Flash: Raccoon SVG benchmark
Researcher observations

The sunset palette and silhouetted grouping establish an appealing scene. A masked rider sits above a pointed-eared dog, but merged body shapes leave limbs and support unresolved. The boatlike craft lacks readable steering controls, so the requested action is unclear. Sparse facial marks and glowing spray dots offer limited detail.

Exact prompt

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

GPT 5.556.0/100

GPT 5.5: Raccoon SVG benchmark
Researcher observations

The raccoon's masked face, bright hull and sweeping wake make the scene readable and lively. The dog is much less resolved: its head is ambiguous, overlapping brown forms obscure its anatomy, and its paws do not visibly grip the controls. Smooth shapes and cheerful colors provide appeal, but weak steering construction and limited depth keep the drawing uneven.

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 V4.1 FlashGPT 5.5
Prompt & likeness5.5/106.0/10
Anatomy & construction3.5/104.0/10
Space & placement5.0/106.0/10
Light & reflections6.0/105.5/10
Purposeful detail3.5/105.5/10
Artistry & character5.5/106.5/10
Materials & effects4.0/105.5/10
Visual integrity6.5/106.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence.

DeepSeek V4.1 Flash76.0/100

DeepSeek V4.1 Flash: Pelican SVG benchmark
Researcher observations

A recognizable pelican rides a brightly colored bicycle against a striking sunset. The sweeping bill, trailing scarf and circular wheels create a controlled composition. Both legs connect, but pedal linkage, body support and the wing's handlebar grip remain loosely resolved. Clean vector shapes and feather details work well; simplified shading limits volume and integration with the sunset light.

Exact prompt

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

GPT 5.564.3/100

GPT 5.5: Pelican SVG benchmark
Researcher observations

The oversized bill, bright bicycle and sunset create an appealing, recognizable cartoon. Riding mechanics are less convincing: the wing has no clear steering contact, leg attachments are uneven, and feet do not visibly engage pedals. A dark notch complicates the rear neck junction. Clean contours and orderly spokes provide polish, while simplified anatomy and lighting limit depth.

Exact prompt

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

Compare category scores
CategoryDeepSeek V4.1 FlashGPT 5.5
Prompt & likeness8.5/107.5/10
Anatomy & construction7.0/104.5/10
Space & placement7.5/106.5/10
Light & reflections7.0/106.5/10
Purposeful detail7.5/106.0/10
Artistry & character8.0/107.5/10
Materials & effects7.0/106.0/10
Visual integrity8.0/107.5/10