STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Claude Haiku 5.5 vs Nemotron 3 Ultra

Claude Haiku 5.5 scores 28.6 points higher overall (46.5 vs 17.9). Claude Haiku 5.5 scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

46.5/100
17.9/100

General Intelligence

40.7/100
14.5/100

Visual Intelligence

53.3/100
24.9/100

Newton's Mirror

Same prompt

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

Claude Haiku 5.540.0/100

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

The centered sphere, compact airborne black blob and differentiated cyan/crimson interaction support substantial state and placement credit. The few recognizable sphere and panel images establish limited optical relationships, but most of the required mirror system is missing. Rounded volume and localized paint warrant substantial material credit despite the soft, illustrative finish.

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.

Nemotron 3 Ultra14.1/100

Nemotron 3 Ultra: Newton's Mirror SVG benchmark
Researcher observations

The candidate establishes a separate airborne black blob and partial crimson overlap, but leaves the paint interaction history and settled support unresolved. Its main silhouette, black placement and lamp projection depart substantially from the required camera geometry. A few faint reflection hints provide little support for the extensive mirror system, while the compact paint volumes are visibly disproportionate.

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 Haiku 5.5Nemotron 3 Ultra
State at 600 ms23.5/258.5/25
Camera and placement8.0/153.5/15
Reflections24.5/1206.5/120
Materials and scale7.5/103.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

Claude Haiku 5.546.4/100

Claude Haiku 5.5: Selfie SVG benchmark
Researcher observations

A coherent coral squid emblem with a compact mantle, restrained face and clean centered presentation. Its radial silhouette and floating placement work, but sharp arm tips, crowded roots and sparse surface modeling limit softness, construction and finish.

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.

Nemotron 3 Ultra36.2/100

Nemotron 3 Ultra: Selfie SVG benchmark
Researcher observations

An endearing mechanical creature is clearly framed, with expressive amber eyes and readable segmented arms. The shell resembles layered green plates more than a deep coiled spiral. Detached-looking construction, absent working contacts and patchy rendering leave the central assembly action substantially unresolved.

Prompt withheld

The exact prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryClaude Haiku 5.5Nemotron 3 Ultra
Prompt & likeness6.5/104.0/10
Anatomy & construction4.0/104.0/10
Space & placement6.5/105.5/10
Light & reflections4.0/105.0/10
Purposeful detail3.5/104.0/10
Artistry & character3.0/103.0/10
Materials & effects4.5/104.0/10
Visual integrity8.0/104.5/10

Mona Lisa

Same prompt

Claude Haiku 5.538.6/100

Claude Haiku 5.5: Mona Lisa SVG benchmark
Researcher observations

A recognizable but basic Mona Lisa reinterpretation. Clean contours and smooth facial lighting provide coherence and volume. Replication remains limited by the frontal pose, elongated neck, schematic expression, unresolved crossed hands and sparse landscape. Lighting is more successful than anatomical construction and purposeful detail.

Exact prompt

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

Nemotron 3 Ultra0.5/100

Nemotron 3 Ultra: Mona Lisa SVG benchmark
Researcher observations

The centered silhouette provides basic organization, but multicolored mottling and geometric overlays leave the portrait unresolved. No readable face, crossed hands, clothing or landscape establishes Mona Lisa replication. Texture and transparency offer limited visual effects without coherent anatomy, lighting or material distinctions.

Exact prompt

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

Compare category scores
CategoryClaude Haiku 5.5Nemotron 3 Ultra
Prompt & likeness3.0/100.5/10
Anatomy & construction4.0/100.0/10
Space & placement4.0/101.0/10
Light & reflections5.5/100.5/10
Purposeful detail2.5/100.5/10
Artistry & character3.5/101.5/10
Materials & effects2.5/100.0/10
Visual integrity5.5/100.5/10

Beach

Same prompt

Claude Haiku 5.571.9/100

Claude Haiku 5.5: Beach SVG benchmark
Researcher observations

A cheerful, coherent beach illustration with attractive sunset colors, readable accessories and clean silhouettes. Its sun and sailboat reflections establish useful physical relationships. Simple animal construction, flattened foreground placement, sparse directional shadows and minimally differentiated surfaces limit its drawing refinement.

Exact prompt

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

Nemotron 3 Ultra34.4/100

Nemotron 3 Ultra: Beach SVG benchmark
Researcher observations

A recognizable beach illustration with appealing warm-cool contrast, readable layers and mostly clean shapes. Unresolved seat construction, schematic animals and broad geometric foliage give it an elementary finish. Weakly coordinated reflections and limited material differentiation further constrain depth and atmosphere.

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 Haiku 5.5Nemotron 3 Ultra
Prompt & likeness8.5/106.5/10
Anatomy & construction6.5/102.5/10
Space & placement7.0/104.0/10
Light & reflections7.0/101.5/10
Purposeful detail7.0/103.5/10
Artistry & character7.0/102.0/10
Materials & effects6.0/102.5/10
Visual integrity8.5/106.5/10

Ground Truth

Same prompt

Claude Haiku 5.547.4/100

Claude Haiku 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.

Nemotron 3 Ultra17.8/100

Nemotron 3 Ultra: 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 Haiku 5.547.3/100

Claude Haiku 5.5: Raccoon SVG benchmark
Researcher observations

A tidy, appealing cartoon with recognizable animals and a pleasing sunset palette. Steering lacks visible controls, while schematic limbs and uncertain raccoon support weaken the requested interaction. Shallow vehicle construction, flat character lighting and modest displacement limit physical coherence. Clean shapes and readable identifying details remain strengths.

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

Nemotron 3 Ultra24.3/100

Nemotron 3 Ultra: Raccoon SVG benchmark
Researcher observations

The masked raccoon, dog and orange craft make the scene recognizable, with an appealing sunset palette. Overlapping bodies obscure the riding relationship, and the dog's connection to the controls remains unresolved. Weak water displacement, inconsistent shading and visible shape artifacts limit the finish. Ambiguous attachments do not establish detached limbs or inverted anatomy.

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 Haiku 5.5Nemotron 3 Ultra
Prompt & likeness5.5/103.5/10
Anatomy & construction4.0/101.5/10
Space & placement5.5/104.5/10
Light & reflections4.0/102.0/10
Purposeful detail5.5/103.5/10
Artistry & character4.5/101.5/10
Materials & effects5.5/103.0/10
Visual integrity5.0/102.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for Claude Haiku 5.5 and Nemotron 3 Ultra.

Claude Haiku 5.564.0/100

Claude Haiku 5.5: Pelican SVG benchmark
Researcher observations

A cheerful, recognizable illustration with clean contours and a balanced warm palette. Aligned wheels and readable frame geometry establish the bicycle, but shoulder construction, feet and steering contact remain imprecise. Sparse drivetrain detail, flat materials and absent grounding shadows limit anatomical and spatial conviction.

Exact prompt

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

Nemotron 3 Ultra47.0/100

Nemotron 3 Ultra: Pelican SVG benchmark
Researcher observations

A recognizable, playful pelican dominates a readable bicycle scene. Its bill and silhouette succeed, but feet below the pedals and confused drivetrain connections weaken the riding action. Local material modeling adds interest; overlapping contours, repetitive detail and inconsistent shadows leave the illustration basic and uneven.

Exact prompt

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

Compare category scores
CategoryClaude Haiku 5.5Nemotron 3 Ultra
Prompt & likeness8.0/106.5/10
Anatomy & construction5.5/104.0/10
Space & placement6.5/105.5/10
Light & reflections5.0/104.0/10
Purposeful detail6.0/105.0/10
Artistry & character6.5/105.5/10
Materials & effects5.0/105.5/10
Visual integrity8.0/106.0/10