STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Claude Opus 5.5 vs GPT-6 Astra

GPT-6 Astra scores 2.7 points higher overall (68.7 vs 66.0). GPT-6 Astra scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

66.0/100
68.7/100

General Intelligence

55.3/100
59.0/100

Visual Intelligence

74.5/100
76.1/100

Newton's Mirror

Same prompt

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

Claude Opus 5.552.5/100

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.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

GPT-6 Astra57.8/100

GPT-6 Astra: Newton's Mirror SVG benchmark
Researcher observations

Major placement and the visible contact sequence are convincing. Dense planar light repetition, recognizable spherical panel images and simplified nested sphere motifs provide useful optical structure. Missing outer chains, truncated distant sequences and incorrect bead-like belts still leave the recursive reflections substantially incomplete.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryClaude Opus 5.5GPT-6 Astra
State at 600 ms25.0/2525.0/25
Camera and placement15.0/1515.0/15
Reflections46.5/12054.0/120
Materials and scale8.0/1010.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

Claude Opus 5.578.3/100

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.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

GPT-6 Astra76.0/100

GPT-6 Astra: Selfie SVG benchmark
Researcher observations

The sixfold silhouette, pale coloring, outward heads and central hexagon closely match the brief. Fine scales and soft shading support rounded volume. However, several crossings have conspicuous rectangular seams and weak contact shadows, making the weave feel assembled. Small heads have limited anatomical definition, and the repetitive texture conveys less organic life than requested.

Prompt withheld

This prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryClaude Opus 5.5GPT-6 Astra
Prompt & likeness8.0/108.5/10
Anatomy & construction7.5/107.5/10
Space & placement8.0/107.5/10
Light & reflections7.5/107.0/10
Purposeful detail7.5/107.5/10
Artistry & character8.0/108.0/10
Materials & effects7.5/107.0/10
Visual integrity8.5/107.0/10

Beach

Same prompt

Claude Opus 5.578.0/100

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

GPT-6 Astra76.8/100

GPT-6 Astra: Beach SVG benchmark
Researcher observations

A coherent sunset beach illustration with an inviting palette, strong palm framing and a clear sun reflection. Animals, playing figures and beach equipment provide variety. Simplified human and dog anatomy, weak dolphin splash cues and uneven shadow directions limit physical conviction. Clean silhouettes and small decorative details support an appealing, polished composition.

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 5.5GPT-6 Astra
Prompt & likeness8.5/108.5/10
Anatomy & construction7.5/107.0/10
Space & placement7.0/107.5/10
Light & reflections8.0/107.5/10
Purposeful detail8.0/107.5/10
Artistry & character8.0/108.0/10
Materials & effects6.5/107.5/10
Visual integrity8.5/108.0/10

Mona Lisa

Same prompt

Claude Opus 5.564.8/100

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

GPT-6 Astra67.3/100

GPT-6 Astra: Mona Lisa SVG benchmark
Researcher observations

The crossed hands, restrained smile, dark clothing and hazy landscape clearly recall the Mona Lisa. Replication is limited by the frontal, elongated face, schematic eyes and stiff fingers. Soft shading gives basic volume, but broad garment shapes and angular scenery lack the original’s nuanced depth and painterly transitions. The frame and composition are controlled; surface grain adds texture without resolving the simplified drawing.

Exact prompt

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

Compare category scores
CategoryClaude Opus 5.5GPT-6 Astra
Prompt & likeness7.0/107.0/10
Anatomy & construction6.0/106.0/10
Space & placement6.5/106.5/10
Light & reflections6.0/107.0/10
Purposeful detail6.5/106.5/10
Artistry & character6.5/107.0/10
Materials & effects6.5/107.0/10
Visual integrity7.0/107.5/10

Raccoon

Same prompt

Claude Opus 5.575.0/100

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

GPT-6 Astra79.5/100

GPT-6 Astra: Raccoon SVG benchmark
Researcher observations

Expressive animals, a balanced sunset composition and sweeping wake make an appealing illustration. The raccoon rides the dog's back, and the dog's connected foreleg reaches the controls. The compact steering assembly and layered paws are less clearly constructed. Lighting remains mostly flat, with little shadow or sun reflection. Clean contours and purposeful details support strong illustrative execution.

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 5.5GPT-6 Astra
Prompt & likeness8.5/108.5/10
Anatomy & construction7.0/107.5/10
Space & placement7.5/108.0/10
Light & reflections6.0/106.5/10
Purposeful detail7.5/108.0/10
Artistry & character8.0/108.5/10
Materials & effects7.0/108.0/10
Visual integrity8.0/108.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence.

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

GPT-6 Astra75.8/100

GPT-6 Astra: Pelican SVG benchmark
Researcher observations

The pelican's long bill, flowing scarf and warm coastal palette create a charming, balanced illustration. Wheels, spokes and frame are largely coherent, but neither wing reaches the handlebars, and the rear leg's pedal contact is unclear. Flat lighting and simplified surfaces limit depth despite clean outlines and attractive feather detail.

Exact prompt

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

Compare category scores
CategoryClaude Opus 5.5GPT-6 Astra
Prompt & likeness8.5/108.0/10
Anatomy & construction6.5/106.5/10
Space & placement7.0/107.5/10
Light & reflections6.0/107.0/10
Purposeful detail7.5/108.0/10
Artistry & character7.5/108.5/10
Materials & effects6.0/107.5/10
Visual integrity8.5/108.0/10