STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Claude Fable 5.1 vs Kolibri 1

Claude Fable 5.1 scores 49.2 points higher overall (62.2 vs 13.0). Claude Fable 5.1 scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

62.2/100
13.0/100

General Intelligence

58.4/100
12.1/100

Visual Intelligence

66.8/100
14.2/100

Newton's Mirror

Same prompt

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

Claude Fable 5.153.8/100

Claude Fable 5.1: Newton's Mirror SVG benchmark
Researcher observations

The broad paint sequence, bilateral near-field sphere arrangement, overlaps and diminishing panel repetitions are recognizable; crimson is slightly too low. Small paint scale and basic shading provide material cues, although the steel response remains soft. Inaccurate light projections, missing outer chains and incomplete nested room imagery remain the principal limitations.

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.

Kolibri 19.9/100

Kolibri 1: Newton's Mirror SVG benchmark
Researcher observations

A segmented gray perimeter surrounds a black field containing one large, low-positioned gray sphere and two small colored circles. Rounded volume and restrained paint scale earn partial material credit. The image does not demonstrate the required optical structure, while paint history, airborne black and settled support remain largely unresolved.

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 Fable 5.1Kolibri 1
State at 600 ms24.0/258.5/25
Camera and placement14.0/151.5/15
Reflections48.0/1200.0/120
Materials and scale7.0/103.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

Claude Fable 5.167.8/100

Claude Fable 5.1: Selfie SVG benchmark
Researcher observations

The coral palette, friendly face, matte shading and cream arch create a coherent emblem. However, the mantle is elongated rather than compact, and the appendages spread mostly sideways and downward instead of forming an evenly spaced, flower-like starburst. Two thin hanging appendages weaken the thick-arm motif. Clean contours and balanced framing support the simple design.

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.

Kolibri 122.9/100

Kolibri 1: Selfie SVG benchmark
Researcher observations

A restrained ivory, teal and green palette gives the image simple graphic coherence. Execution remains rudimentary: detached oval wings, ambiguous central anatomy and unclear feeding contact prevent a convincing hummingbird scene. The requested feather structure, botanical detail, lighting and enclosing arch are largely unresolved.

Prompt withheld

The exact prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryClaude Fable 5.1Kolibri 1
Prompt & likeness6.5/102.5/10
Anatomy & construction6.5/102.0/10
Space & placement7.5/103.0/10
Light & reflections6.5/102.0/10
Purposeful detail6.0/101.5/10
Artistry & character7.5/101.5/10
Materials & effects6.5/102.0/10
Visual integrity8.0/105.5/10

Mona Lisa

Different prompts

Claude Fable 5.157.6/100

Claude Fable 5.1: Mona Lisa SVG benchmark
Researcher observations

The dark clothing, crossed hands and hazy landscape establish the Mona Lisa composition. Replication is limited by the frontal, elongated face, wide eyes and simplified smile. Rounded, parallel fingers and unclear wrist transitions weaken the hands. Warm facial shading gives some volume, but broad garment shapes and scattered crack marks substitute for convincing folds and painterly detail.

Exact prompt

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

Kolibri 13.3/100

Kolibri 1: Mona Lisa SVG benchmark
Researcher observations

The candidate offers a clean, highly simplified frontal portrait with warm skin and dark hair. Its oversized oval face, schematic features and unresolved body provide little Mona Lisa likeness. Missing crossed hands, clothing detail and landscape remove essential parts of the original composition; smooth gradients supply only limited volume.

Exact prompt

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

Compare category scores
CategoryClaude Fable 5.1Kolibri 1
Prompt & likeness5.5/100.5/10
Anatomy & construction6.0/100.5/10
Space & placement6.0/100.0/10
Light & reflections6.0/100.0/10
Purposeful detail5.0/100.0/10
Artistry & character5.5/100.5/10
Materials & effects6.0/100.5/10
Visual integrity6.5/100.5/10

Beach

Same prompt

Claude Fable 5.173.8/100

Claude Fable 5.1: Beach SVG benchmark
Researcher observations

The colorful sunset, layered shoreline, animals, kite and beach toys fulfill the lively beach brief. Clean silhouettes and a balanced composition give the illustration character. Construction is simplified: the umbrella resembles a segmented fan, dolphins have weak water interaction, and the sun’s reflection forms a rigid widening wedge. Flat surfaces and sparse contact shadows limit depth.

Exact prompt

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

Kolibri 112.9/100

Kolibri 1: Beach SVG benchmark
Researcher observations

A recognizable sunset beach has an appealing purple-orange gradient and clean geometric edges. Birds and animals remain unresolved, terrain obscures the relationship between shore and water, and reflections are absent. Sparse detail, flat materials and limited activity keep the drawing elementary despite its tidy rendering.

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 Fable 5.1Kolibri 1
Prompt & likeness8.5/102.5/10
Anatomy & construction7.0/100.5/10
Space & placement7.0/103.0/10
Light & reflections7.0/101.0/10
Purposeful detail7.5/100.5/10
Artistry & character7.5/101.0/10
Materials & effects6.5/100.5/10
Visual integrity7.5/103.0/10

Ground Truth

Same prompt

Claude Fable 5.163.8/100

Claude Fable 5.1: 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.

Kolibri 120.7/100

Kolibri 1: 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 Fable 5.170.0/100

Claude Fable 5.1: Raccoon SVG benchmark
Researcher observations

The raccoon rides on the dog's back, and the dog's extended foreleg reaches the jet ski controls. Expressive faces, a clear silhouette and sweeping spray make the action readable. Limb and handlebar overlaps weaken construction; broad shading provides limited volume, and the glowing sun has little corresponding reflection on the water. Clean vector shapes support an appealing but simplified illustration.

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

Kolibri 110.0/100

Kolibri 1: Raccoon SVG benchmark
Researcher observations

Clean shapes and a readable coral platform provide basic graphic clarity, but the animal construction remains fragmented. A recognizable raccoon riding the dog's back, connected steering and convincing water contact are not demonstrated. Sparse detail, flat subjects and absent movement effects support retaining the baseline category assessments.

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 Fable 5.1Kolibri 1
Prompt & likeness8.5/101.5/10
Anatomy & construction6.5/101.0/10
Space & placement7.0/101.0/10
Light & reflections5.5/100.0/10
Purposeful detail7.0/100.5/10
Artistry & character7.5/100.5/10
Materials & effects6.5/100.5/10
Visual integrity7.5/103.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for Claude Fable 5.1 and Kolibri 1.

Claude Fable 5.172.3/100

Claude Fable 5.1: Pelican SVG benchmark
Researcher observations

The pelican reads clearly, with an expressive face, prominent bill and appealing composition. Both legs connect to the body, but the far foot's pedal contact and the wing's steering grip remain unclear. Wheel alignment and background layers are coherent. Clean contours and feather lines give polish, while schematic machinery, limited surface texture and weak directional lighting constrain the finish.

Exact prompt

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

Kolibri 135.3/100

Kolibri 1: Pelican SVG benchmark
Researcher observations

Clean shapes and aligned wheels establish a readable schematic scene. Pelican likeness, riding support and bicycle mechanics remain substantially unresolved. Sparse detail and flat surfaces limit expression and volume. Strong edge and fill integrity is a separate success and does not repair the construction.

Exact prompt

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

Compare category scores
CategoryClaude Fable 5.1Kolibri 1
Prompt & likeness8.5/103.5/10
Anatomy & construction6.5/102.0/10
Space & placement7.5/104.0/10
Light & reflections6.0/103.0/10
Purposeful detail7.0/102.5/10
Artistry & character7.5/103.0/10
Materials & effects6.0/103.0/10
Visual integrity8.0/108.5/10