STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Claude Opus 5.5 vs Qwen3.5 9B

Claude Opus 5.5 scores 58.7 points higher overall (69.7 vs 11.0). Claude Opus 5.5 scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

69.7/100
11.0/100

General Intelligence

66.2/100
8.2/100

Visual Intelligence

73.9/100
14.3/100

Newton's Mirror

Same prompt

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

Claude Opus 5.555.7/100

Claude Opus 5.5: Newton's Mirror SVG benchmark
Researcher observations

Open lateral sightlines, first reflected silhouettes and near-field planar panel placement are convincing. Missing outer chains, truncated repetitions and absent nested spherical room and emitter imagery remain the main weaknesses.

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.

Qwen3.5 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.

Compare category scores
CategoryClaude Opus 5.5Qwen3.5 9B
State at 600 ms25.0/255.5/25
Camera and placement15.0/154.5/15
Reflections46.5/1202.0/120
Materials and scale8.0/103.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

Claude Opus 5.577.6/100

Claude Opus 5.5: Selfie SVG benchmark
Researcher observations

The centered coral squid has a friendly, restrained expression and a balanced radial silhouette within a cream arch. Smooth curves and soft shading give it an appealing matte finish. The mantle is more elongated than compact, the upper arms are visually ambiguous, and the two hanging tentacles read somewhat like legs. Clean execution supports a strong stylized illustration.

Simplified prompt

Draw a calm coral-red squid with eight thick arms spreading around it like flower petals. Keep the shape balanced and simple, with soft shading and a friendly face.

The exact prompt is held back to prevent benchmaxxing.

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.

Compare category scores
CategoryClaude Opus 5.5Qwen3.5 9B
Prompt & likeness8.0/103.0/10
Anatomy & construction7.5/102.0/10
Space & placement8.0/103.0/10
Light & reflections7.5/103.5/10
Purposeful detail7.5/102.0/10
Artistry & character8.0/102.0/10
Materials & effects7.5/104.0/10
Visual integrity8.5/103.0/10

Mona Lisa

Different prompts

Claude Opus 5.562.5/100

Claude Opus 5.5: Mona Lisa SVG benchmark
Researcher observations

The portrait preserves the recognizable composition, dark veil, folded hands and distant landscape. Replication is limited by the elongated face and neck, conspicuous eyes and simplified smile. Hands remain connected but their rounded fingers and wrists lack convincing anatomy. Restrained colors create cohesion; shallow modeling and pervasive mottling weaken volume and painterly subtlety.

Exact prompt

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

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

Compare category scores
CategoryClaude Opus 5.5Qwen3.5 9B
Prompt & likeness6.5/100.0/10
Anatomy & construction5.5/100.0/10
Space & placement6.5/100.0/10
Light & reflections6.5/100.0/10
Purposeful detail6.5/100.0/10
Artistry & character6.0/100.5/10
Materials & effects7.0/100.0/10
Visual integrity7.0/100.5/10

Beach

Same prompt

Claude Opus 5.577.0/100

Claude Opus 5.5: Beach SVG benchmark
Researcher observations

A lively, well-composed beach illustration with rich sunset colors, recognizable animals and appealing accessories. The sun reflection establishes a strong central focus. Clean silhouettes and small details reward inspection, though simplified animal construction, uneven contact shadows and mostly flat materials limit depth and realism.

Exact prompt

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

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

Compare category scores
CategoryClaude Opus 5.5Qwen3.5 9B
Prompt & likeness8.5/101.5/10
Anatomy & construction7.5/100.5/10
Space & placement7.0/101.5/10
Light & reflections7.5/101.0/10
Purposeful detail7.5/102.5/10
Artistry & character8.0/101.5/10
Materials & effects6.5/100.5/10
Visual integrity8.0/101.5/10

Ground Truth

Same prompt

Claude Opus 5.580.2/100

Claude Opus 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.

Qwen3.5 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.

Raccoon

Same prompt

Claude Opus 5.576.0/100

Claude Opus 5.5: Raccoon SVG benchmark
Researcher observations

The masked raccoon clearly rides the dog's back, and the dog's forward paw reaches the steering grip. Expressive faces, vivid colors and sweeping wakes create an appealing illustration. Connected limbs remain schematic, as does the small steering assembly. The broad hull and flat foam weaken water contact; the glowing sun lacks a corresponding reflection or convincing cast shadows.

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

Qwen3.5 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

Compare category scores
CategoryClaude Opus 5.5Qwen3.5 9B
Prompt & likeness8.5/102.5/10
Anatomy & construction7.5/101.0/10
Space & placement7.5/102.0/10
Light & reflections6.0/101.0/10
Purposeful detail8.5/101.5/10
Artistry & character7.5/101.0/10
Materials & effects7.0/101.0/10
Visual integrity8.0/102.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for Claude Opus 5.5 and Qwen3.5 9B.

Claude Opus 5.572.5/100

Claude Opus 5.5: Pelican SVG benchmark
Researcher observations

The recognizable pelican, orderly bicycle wheels and harmonious sunset create an appealing illustration. Both legs connect to the body and reach pedals; no clear detached or inverted parts appear. Steering contact and seating support are less convincing, while the drivetrain remains schematic. Crisp outlines give a clean finish, but limited shading and flat surfaces leave the scene with modest depth.

Exact prompt

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

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

Compare category scores
CategoryClaude Opus 5.5Qwen3.5 9B
Prompt & likeness8.5/105.0/10
Anatomy & construction6.5/102.5/10
Space & placement7.0/104.0/10
Light & reflections6.0/102.5/10
Purposeful detail7.5/103.0/10
Artistry & character7.5/103.5/10
Materials & effects6.0/102.5/10
Visual integrity8.5/105.0/10