STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT 5.5 vs Qwen3.6 27b

Qwen3.6 27b scores 1.2 points higher overall (33.3 vs 32.1). GPT 5.5 leads General Intelligence; Qwen3.6 27b leads Visual Intelligence. Qwen3.6 27b scores higher on Beach, with its largest category advantage in anatomy & construction.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

32.1/100
33.3/100

General Intelligence

28.1/100
21.9/100

Visual Intelligence

36.8/100
46.8/100

Newton's Mirror

Same prompt

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

GPT 5.525.4/100

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.

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.

Qwen3.6 27b17.0/100

Qwen3.6 27b: Newton's Mirror SVG benchmark
Researcher observations

The artwork depicts a shaded sphere, distinct paint colors and a separate airborne black blob. Crimson's apex overlap does not establish its earlier interaction and transport, while cyan's recent contact remains unsupported. Horizontal centering supplies limited camera agreement, but the sphere, black blob and prominent panel have substantial placement or projection departures. A few planar echoes provide reflection evidence; isolated patches and gradients replace most of the required mirror structure.

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
CategoryGPT 5.5Qwen3.6 27b
State at 600 ms19.5/258.0/25
Camera and placement7.0/155.0/15
Reflections5.0/1208.0/120
Materials and scale6.0/104.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

GPT 5.541.2/100

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.

Simplified prompt

Draw a pale six-headed snake woven into a symmetrical knot. Its body passes over and under itself around a small hexagonal opening, with six little heads facing outward. Add lifelike scales, curved muscles and shadows without losing the clear knot shape.

The exact prompt is held back to prevent benchmaxxing.

Qwen3.6 27b56.3/100

Qwen3.6 27b: Selfie SVG benchmark
Researcher observations

An appealing decorative illustration with coordinated ornament, flowing panels and three glowing orbital lights. The arm arrangement reverses the requested sides. Uncertain neck continuity, concealed leg articulation, simplified paws, crowded chest jewelry and shallow surface modeling limit pose clarity and finish.

Simplified prompt

Draw a friendly capybara floating in ornate green and white robes. A glowing halo and small floating orbs surround it, giving it the feel of a gentle fantasy guide.

The exact prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryGPT 5.5Qwen3.6 27b
Prompt & likeness2.5/106.5/10
Anatomy & construction3.0/105.0/10
Space & placement5.0/106.5/10
Light & reflections5.0/105.5/10
Purposeful detail4.5/106.0/10
Artistry & character4.0/105.0/10
Materials & effects4.5/105.0/10
Visual integrity7.0/106.5/10

Mona Lisa

Different prompts

GPT 5.517.3/100

GPT 5.5: Mona Lisa SVG benchmark
Researcher observations

The veil, restrained smile, crossed hands and muted landscape establish Mona Lisa references. The oversized frontal face and schematic features weaken likeness and expression, while fingerless tapered hand shapes leave anatomy unresolved. Clean contours and balanced framing provide coherence, but sparse garment detail, broad landscape bands and shallow shading limit the portrait's sophistication.

Exact prompt

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

Qwen3.6 27b30.8/100

Qwen3.6 27b: Mona Lisa SVG benchmark
Researcher observations

The portrait loosely evokes Mona Lisa through its palette and silhouette. Readable pupils, brows and lips provide limited detail, and the torso remains continuous. The frontal elongated face, unresolved chest-level limb forms, shallow landscape and pervasive blur substantially weaken likeness, anatomy and finish.

Exact prompt

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

Compare category scores
CategoryGPT 5.5Qwen3.6 27b
Prompt & likeness1.5/102.5/10
Anatomy & construction1.5/103.0/10
Space & placement1.5/104.0/10
Light & reflections2.0/104.0/10
Purposeful detail2.5/102.5/10
Artistry & character1.5/102.5/10
Materials & effects2.0/103.0/10
Visual integrity1.5/104.0/10

Beach

Same prompt

GPT 5.535.6/100

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 is underdeveloped: torso and limb connections are unclear, especially in the round-eared foreground figure. 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

Qwen3.6 27b56.7/100

Qwen3.6 27b: Beach SVG benchmark
Researcher observations

A recognizable sunset beach with balanced palms, clean shapes and effective warm–cool contrast. Small animals and play equipment address the brief, but rudimentary anatomy, uncertain water contacts, sparse reflections and flat materials keep the drawing basic or uneven.

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
CategoryGPT 5.5Qwen3.6 27b
Prompt & likeness7.5/107.5/10
Anatomy & construction2.5/105.0/10
Space & placement3.0/105.5/10
Light & reflections3.0/105.5/10
Purposeful detail3.0/104.5/10
Artistry & character3.0/105.5/10
Materials & effects3.0/105.5/10
Visual integrity3.5/107.0/10

Ground Truth

Same prompt

GPT 5.539.2/100

GPT 5.5: 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.

Qwen3.6 27b23.7/100

Qwen3.6 27b: 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

GPT 5.543.7/100

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

Qwen3.6 27b57.7/100

Qwen3.6 27b: Raccoon SVG benchmark
Researcher observations

A readable cartoon with balanced colors, clean shapes and a clearly supported raccoon. Continuous body construction and modest shading deserve credit. Rudimentary limbs, unresolved steering connections, stiff gestures and schematic water effects limit physical credibility and finish.

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
CategoryGPT 5.5Qwen3.6 27b
Prompt & likeness6.0/106.5/10
Anatomy & construction3.0/105.0/10
Space & placement5.0/106.0/10
Light & reflections5.5/105.5/10
Purposeful detail3.5/105.5/10
Artistry & character3.0/106.0/10
Materials & effects5.5/105.5/10
Visual integrity6.5/107.0/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for GPT 5.5 and Qwen3.6 27b.

GPT 5.561.5/100

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

Qwen3.6 27b58.5/100

Qwen3.6 27b: Pelican SVG benchmark
Researcher observations

A lively, coherent illustration with recognizable pelican features, purposeful accessories and useful surface variation. Ambiguous neck layering, uncertain pedal engagement and an unresolved drivetrain limit construction. Aligned wheels and layered scenery establish placement, while inconsistent shadow direction and crowded overlaps constrain finish.

Exact prompt

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

Compare category scores
CategoryGPT 5.5Qwen3.6 27b
Prompt & likeness7.5/107.5/10
Anatomy & construction4.5/104.0/10
Space & placement6.5/106.5/10
Light & reflections6.5/105.0/10
Purposeful detail5.5/106.5/10
Artistry & character6.0/105.5/10
Materials & effects6.0/106.5/10
Visual integrity7.5/106.5/10