STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT 5.6 Luna vs Qwen3.6 35B A3B

GPT 5.6 Luna scores 13.4 points higher overall (38.9 vs 25.5). GPT 5.6 Luna 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

38.9/100
25.5/100

General Intelligence

25.7/100
14.8/100

Visual Intelligence

54.7/100
38.1/100

Newton's Mirror

Same prompt

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

GPT 5.6 Luna27.7/100

GPT 5.6 Luna: Newton's Mirror SVG benchmark
Researcher observations

The room enclosure has coherent symmetric perspective, with the overhead panel, sphere and black aligned centrally. The sphere and airborne black occupy substantially lower positions than the reference framing, inconsistent with the prescribed camera aim. The diagonal crimson streak does not establish the required surface transport. Faint wall sphere images provide limited mirrored correspondence, but the shallow floor image, missing receding chains, absent nested sphere imagery and sparse emitter mapping leave most reflection structure unsupported.

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 35B A3B13.3/100

Qwen3.6 35B A3B: Newton's Mirror SVG benchmark
Researcher observations

The artwork demonstrates rounded volume, recognizable paint colors and a compact black feature at an appropriate screen height. The enlarged main-sphere framing, unsupported crimson and cyan interaction histories, oversized compact paint balls and largely missing mirror structure remain substantial weaknesses. The core assessment is 20/170; with no demonstrated floor damage, the combined assessment remains 20/180.

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 5.6 LunaQwen3.6 35B A3B
State at 600 ms15.0/258.0/25
Camera and placement4.0/154.0/15
Reflections3.5/1205.0/120
Materials and scale10.0/103.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

GPT 5.6 Luna59.8/100

GPT 5.6 Luna: Selfie SVG benchmark
Researcher observations

Six pale, outward-facing heads and six rounded lobes make the knot recognizable. The central hexagonal opening remains clear. However, broad gray crossing panels flatten the weave, several inner joins resemble capped strips, and sparse oversized scale marks leave the bodies looking more like decorated ribbons than living snakes.

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 35B A3B66.4/100

Qwen3.6 35B A3B: Selfie SVG benchmark
Researcher observations

An appealing fantasy illustration with coordinated ornament, readable suspension and luminous turquoise accents. Plausible limb attachments and soft shading support competent execution. Bear-like proportions, unclear paw gestures, insufficient white robe fabric, crowded chest details and shallow material modeling limit its 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 5.6 LunaQwen3.6 35B A3B
Prompt & likeness7.5/106.0/10
Anatomy & construction6.0/106.5/10
Space & placement6.5/107.0/10
Light & reflections5.0/107.0/10
Purposeful detail5.5/106.5/10
Artistry & character6.0/106.5/10
Materials & effects5.0/107.0/10
Visual integrity6.0/107.5/10

Mona Lisa

Different prompts

GPT 5.6 Luna37.1/100

GPT 5.6 Luna: Mona Lisa SVG benchmark
Researcher observations

The central portrait, dark clothing, crossed hands and muted landscape clearly evoke Mona Lisa. Replication is limited by the elongated face, conspicuous eyes and simplified smile. Overlapping fingers have uncertain anatomy, while broad gradients and heavy outlines flatten the portrait. The composition and restrained palette remain coherent.

Exact prompt

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

Qwen3.6 35B A3B12.6/100

Qwen3.6 35B A3B: Mona Lisa SVG benchmark
Researcher observations

A recognizable but basic geometric interpretation. Muted colors and soft shading provide cohesion, while weak likeness, unresolved hands, rigid anatomy and shallow landscape construction substantially limit the replication.

Exact prompt

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

Compare category scores
CategoryGPT 5.6 LunaQwen3.6 35B A3B
Prompt & likeness3.5/102.0/10
Anatomy & construction3.0/100.5/10
Space & placement4.0/102.0/10
Light & reflections4.5/100.5/10
Purposeful detail4.0/101.5/10
Artistry & character3.5/101.5/10
Materials & effects3.5/101.5/10
Visual integrity4.5/102.0/10

Beach

Same prompt

GPT 5.6 Luna47.7/100

GPT 5.6 Luna: Beach SVG benchmark
Researcher observations

The warm sunset, palm silhouette and varied beach activities create an appealing, readable composition. Animals, birds and a broad sun reflection satisfy the brief. Drawing remains elementary: angular airborne sea animals lack splash or convincing motion, the crab's claws are awkwardly constructed, and repeated reflection bands suggest a stepped platform. Clean outlines and pleasant colors exceed the anatomical and spatial sophistication.

Exact prompt

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

Qwen3.6 35B A3B50.7/100

Qwen3.6 35B A3B: Beach SVG benchmark
Researcher observations

A recognizable beach sunset with balanced framing and appealing color transitions. Birds, boats and small animals fulfill the main scene requirements. Elementary anatomy, faint details, weak grounding and rigid reflection columns 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

Compare category scores
CategoryGPT 5.6 LunaQwen3.6 35B A3B
Prompt & likeness7.5/107.5/10
Anatomy & construction4.0/104.5/10
Space & placement6.5/105.5/10
Light & reflections4.0/104.5/10
Purposeful detail5.5/104.5/10
Artistry & character4.0/104.5/10
Materials & effects4.0/105.5/10
Visual integrity3.5/105.0/10

Ground Truth

Same prompt

GPT 5.6 Luna30.0/100

GPT 5.6 Luna: 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 35B A3B10.9/100

Qwen3.6 35B A3B: 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 5.6 Luna65.0/100

GPT 5.6 Luna: Raccoon SVG benchmark
Researcher observations

Expressive animals, a striped tail and clean outlines make the scene appealing and readable. The raccoon sits convincingly on the dog's back, but the overlapping steering paws are ambiguous and the control stem stops above the hull. Broad wake shapes suggest motion; the glowing sun lacks a corresponding water reflection.

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 35B A3B51.9/100

Qwen3.6 35B A3B: Raccoon SVG benchmark
Researcher observations

Clean shapes, cheerful faces and bright colors make the riding arrangement readable. The dog does not visibly operate the control, while awkward limbs, shallow hull placement and stiff poses limit credibility. Gradients and layered foam add modest volume and motion. The obscured tail attachment does not establish detachment.

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 5.6 LunaQwen3.6 35B A3B
Prompt & likeness7.0/106.5/10
Anatomy & construction6.5/104.0/10
Space & placement7.0/106.0/10
Light & reflections6.0/105.5/10
Purposeful detail7.5/104.5/10
Artistry & character5.5/104.0/10
Materials & effects6.5/106.0/10
Visual integrity6.5/108.0/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for GPT 5.6 Luna and Qwen3.6 35B A3B.

GPT 5.6 Luna76.0/100

GPT 5.6 Luna: Pelican SVG benchmark
Researcher observations

A recognizable pelican cyclist with an expressive profile, balanced composition and controlled outlines. Head, neck and torso connect coherently. The bicycle wheels and frame are convincing, but overlapping feet obscure pedal contact, the drivetrain lacks a clear chain, and the wing's handlebar grip is schematic. Atmospheric color succeeds more strongly than directional lighting or material depth.

Exact prompt

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

Qwen3.6 35B A3B61.5/100

Qwen3.6 35B A3B: Pelican SVG benchmark
Researcher observations

A cheerful, readable illustration with a distinctive pelican silhouette, clean contours and an orderly landscape. Soft glow and restrained shading provide modest atmosphere. Construction is weaker: the handlebar is disconnected, wings do not reach the controls, and overlapping legs leave pedaling ambiguous. Simple forms and mostly flat materials limit depth and drawing sophistication.

Exact prompt

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

Compare category scores
CategoryGPT 5.6 LunaQwen3.6 35B A3B
Prompt & likeness8.5/107.0/10
Anatomy & construction7.0/104.5/10
Space & placement7.5/106.5/10
Light & reflections6.5/106.0/10
Purposeful detail7.5/105.5/10
Artistry & character8.0/106.5/10
Materials & effects7.0/106.0/10
Visual integrity8.5/108.0/10