STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Qwen3.5 9B vs Qwen3.8 Max 0902

Qwen3.8 Max 0902 scores 45.4 points higher overall (56.4 vs 11.0). Qwen3.8 Max 0902 scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

11.0/100
56.4/100

General Intelligence

8.2/100
50.7/100

Visual Intelligence

14.3/100
63.1/100

Newton's Mirror

Same prompt

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

Qwen3.5 9B10.9/100

Qwen3.5 9B: Newton's Mirror SVG benchmark
Researcher observations

Horizontal centering and a separate airborne black blob are visible. Cyan's recent contact and crimson's forward transport are insufficiently demonstrated, while sphere support remains obscured. The enlarged, lowered sphere substantially changes the composition. The wall and floor sphere images, recursive room structure and curved emitter mappings are almost entirely missing.

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.

Qwen3.8 Max 090238.7/100

Qwen3.8 Max 0902: Newton's Mirror SVG benchmark
Researcher observations

The central sphere and differentiated cyan/crimson interaction are supported. The tiny highlighted object above the sphere provides partial airborne-black evidence. The few isolated sphere and panel images preserve limited optical relationships, but most of the repeating mirror-room structure is missing. Core score: 64.5/170; including the floor-damage reward: 64.5/180.

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
CategoryQwen3.5 9BQwen3.8 Max 0902
State at 600 ms5.5/2523.5/25
Camera and placement4.5/1511.0/15
Reflections2.0/12024.0/120
Materials and scale3.0/106.0/10
Floor-damage reward0.0/100.0/10

Selfie

Same prompt

Qwen3.5 9B25.8/100

Qwen3.5 9B: Selfie SVG benchmark
Researcher observations

Glowing teal spheres and a harmonious palette provide visible strengths, but the central character remains seriously unresolved. A large gap separates head and torso, limbs cannot be traced, and scattered garment shapes fail to establish the ornate costume. The foreground mound replaces the tall enclosing arch. Clean primitive edges do not repair these construction failures.

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.

Qwen3.8 Max 090272.6/100

Qwen3.8 Max 0902: Selfie SVG benchmark
Researcher observations

A coherent ornamental illustration with balanced framing, appealing color and legible magical accessories. The disconnected raised wrist, incorrect raised-arm side and palm orientation, bear-like facial proportions and shallow material modeling limit execution. Clean decoration and compact spatial balance remain strengths.

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
CategoryQwen3.5 9BQwen3.8 Max 0902
Prompt & likeness3.0/107.5/10
Anatomy & construction2.0/106.5/10
Space & placement3.0/108.0/10
Light & reflections3.5/107.0/10
Purposeful detail2.0/108.0/10
Artistry & character2.0/107.0/10
Materials & effects4.0/107.5/10
Visual integrity3.0/108.0/10

Mona Lisa

Same prompt

Qwen3.5 9B1.2/100

Qwen3.5 9B: Mona Lisa SVG benchmark
Researcher observations

A centered dark oval with sparse facial marks forms a simple graphic face, but scarcely replicates the Mona Lisa. The portrait's body, crossed hands, clothing and landscape are missing, while angular facial construction and flat tones lose its likeness, volume and subtle expression.

Exact prompt

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

Qwen3.8 Max 090245.1/100

Qwen3.8 Max 0902: Mona Lisa SVG benchmark
Researcher observations

A recognizable, cohesive Mona Lisa interpretation with readable landscape layers and a restrained expression. Continuous body construction and clean contours support readability, but broad hands, simplified drapery, frontal symmetry and limited facial volume keep the execution basic and uneven.

Exact prompt

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

Compare category scores
CategoryQwen3.5 9BQwen3.8 Max 0902
Prompt & likeness0.0/104.5/10
Anatomy & construction0.0/103.5/10
Space & placement0.0/105.0/10
Light & reflections0.0/105.0/10
Purposeful detail0.0/105.0/10
Artistry & character0.5/105.0/10
Materials & effects0.0/103.5/10
Visual integrity0.5/105.0/10

Beach

Same prompt

Qwen3.5 9B12.8/100

Qwen3.5 9B: Beach SVG benchmark
Researcher observations

The beach is recognizable, and sweeping shoreline curves provide basic rhythm. Wildlife and playful activity remain poorly resolved, with ambiguous body construction and object contact. The sun glows without corresponding reflections or surface lighting. Fragmented subjects and an unintegrated rectangular panel substantially weaken composition and finish.

Exact prompt

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

Qwen3.8 Max 090277.7/100

Qwen3.8 Max 0902: Beach SVG benchmark
Researcher observations

A strong stylized beach illustration with coherent sunset color, lively dolphin arcs and balanced activity. Clean contours, readable ground contact and an aligned reflection support the finish. Schematic anatomy, sparse small-subject features, flat materials and repetitive water highlights limit physical depth and refinement.

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
CategoryQwen3.5 9BQwen3.8 Max 0902
Prompt & likeness1.5/108.5/10
Anatomy & construction0.5/107.5/10
Space & placement1.5/107.5/10
Light & reflections1.0/108.0/10
Purposeful detail2.5/107.0/10
Artistry & character1.5/108.0/10
Materials & effects0.5/106.5/10
Visual integrity1.5/108.5/10

Ground Truth

Same prompt

Qwen3.5 9B10.4/100

Qwen3.5 9B: 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.

Qwen3.8 Max 090261.6/100

Qwen3.8 Max 0902: 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

Qwen3.5 9B14.7/100

Qwen3.5 9B: Raccoon SVG benchmark
Researcher observations

Bright colors, clean individual shapes and basic animal cues make the scene partly recognizable. Back seating, body continuity, steering and jet ski construction remain unresolved. Background gradients and wave rhythm provide some finish, but substantial anatomical, spatial and interaction weaknesses dominate.

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

Qwen3.8 Max 090269.9/100

Qwen3.8 Max 0902: Raccoon SVG benchmark
Researcher observations

The riding arrangement and steering action are readable, supported by coherent visible attachments and useful character details. Clean shapes, strong color separation and clustered foam make the scene appealing and active. Stiff anatomy, crowded controls, limited directional lighting and simple surface treatments constrain sophistication.

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
CategoryQwen3.5 9BQwen3.8 Max 0902
Prompt & likeness2.5/108.0/10
Anatomy & construction1.0/107.0/10
Space & placement2.0/107.0/10
Light & reflections1.0/106.5/10
Purposeful detail1.5/107.0/10
Artistry & character1.0/106.5/10
Materials & effects1.0/106.0/10
Visual integrity2.5/107.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for Qwen3.5 9B and Qwen3.8 Max 0902.

Qwen3.5 9B35.5/100

Qwen3.5 9B: Pelican SVG benchmark
Researcher observations

The oversized bill and orderly spoked wheels make the subject partly recognizable. Clean contours and strong color contrast provide graphic clarity, but unresolved appendages, steering, drivetrain and support dominate the construction. Sparse shading and detail further limit the illustration.

Exact prompt

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

Qwen3.8 Max 090271.5/100

Qwen3.8 Max 0902: Pelican SVG benchmark
Researcher observations

An appealing graphic illustration with a recognizable pelican, readable bicycle and clean coastal composition. Steering contact and one connected pedal support the action. Ambiguous neck-to-torso construction, an unclear opposing pedal connection, shallow space and limited material and lighting effects constrain its execution.

Exact prompt

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

Compare category scores
CategoryQwen3.5 9BQwen3.8 Max 0902
Prompt & likeness5.0/108.5/10
Anatomy & construction2.5/106.5/10
Space & placement4.0/107.0/10
Light & reflections2.5/106.0/10
Purposeful detail3.0/107.0/10
Artistry & character3.5/107.5/10
Materials & effects2.5/106.0/10
Visual integrity5.0/108.0/10