STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT 6.1 Sol vs Mai Thinking 1

GPT 6.1 Sol scores 45.2 points higher overall (64.7 vs 19.5). GPT 6.1 Sol scores higher on Newton's Mirror, with its largest category advantage in reflections.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

64.7/100
19.5/100

General Intelligence

56.4/100
10.0/100

Visual Intelligence

74.5/100
30.8/100

Newton's Mirror

Same prompt

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

GPT 6.1 Sol50.5/100

GPT 6.1 Sol: Newton's Mirror SVG benchmark
Researcher observations

Recognizable first sphere images and several central planar lights provide limited geometric agreement. Missing outer chains, truncated panel sequences and simplified interiors across the main, side and floor spheres leave most of the recursive reflection structure unsupported.

Benchmark task

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.

Mai Thinking 115.7/100

Mai Thinking 1: Newton's Mirror SVG benchmark
Researcher observations

The small paint features and convex shading deserve moderate material credit. The sphere remains undersized and low, with black unusually close to its apex. Crimson and cyan do not establish the required impact histories. Faint reflected echoes supply limited optical evidence, while the defining recursive room, nested sphere and emitter structures remain unestablished.

Benchmark task

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.

Compare category scores
CategoryGPT 6.1 SolMai Thinking 1
State at 600 ms25.0/257.5/25
Camera and placement15.0/153.5/15
Reflections29.0/1204.0/120
Materials and scale10.0/105.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

GPT 6.1 Sol76.0/100

GPT 6.1 Sol: Selfie SVG benchmark
Researcher observations

Six outward-facing heads and evenly arranged loops make the pale interlocking knot immediately readable. Uniform widths, angular inner bends and fine scales preserve its ornamental geometry. The bodies feel more like textured tubes than living muscle: shading is subdued, crossing contact shadows are weak, and visible curved seams interrupt surface continuity. Small heads have readable eyes and jaws but limited anatomical depth.

Benchmark task

Draw a pale six-headed snake woven into a symmetrical knot. Its body passes over and under itself around a small hexagonal opening, with six little heads facing outward. Add lifelike scales, curved muscles and shadows without losing the clear knot shape.

Mai Thinking 146.3/100

Mai Thinking 1: Selfie SVG benchmark
Researcher observations

A recognizable lantern-and-moth illustration with appealing coloured wings and tidy outer contours. Simple construction, a small focal subject and crowded overlaps limit character and depth. The face, six-leg anatomy, seedling and antenna-driven watering joke remain insufficiently readable.

Prompt withheld

Prompt withheld.

Compare category scores
CategoryGPT 6.1 SolMai Thinking 1
Prompt & likeness8.5/104.0/10
Anatomy & construction7.5/104.5/10
Space & placement8.0/105.0/10
Light & reflections6.5/104.5/10
Purposeful detail7.5/104.0/10
Artistry & character8.0/105.0/10
Materials & effects6.5/105.0/10
Visual integrity8.0/106.0/10

Mona Lisa

Different prompts

GPT 6.1 Sol61.4/100

GPT 6.1 Sol: Mona Lisa SVG benchmark
Researcher observations

The recognizable pose, dark clothing and misty landscape form a coherent portrait. Soft facial shading creates volume, but the broad face, outlined eyes and simplified smile limit likeness. Overlapping hands have flattened fingers and ambiguous separation. Angular landscape shapes and sparse fabric detail keep the execution competent rather than masterful.

Benchmark task

Replicate mona-lisa as SVG

Mai Thinking 111.8/100

Mai Thinking 1: Mona Lisa SVG benchmark
Researcher observations

A recognizable Mona Lisa motif emerges from dark hair, a pale face and a landscape band. Replication remains weak: the oversized frontal head, broad smile, unresolved torso and missing crossed-hand anatomy diverge substantially from the reference. Simple fills and sparse strokes provide limited volume, material definition or painterly complexity.

Benchmark task

Generate an SVG of mona-lisa

Compare category scores
CategoryGPT 6.1 SolMai Thinking 1
Prompt & likeness6.5/101.0/10
Anatomy & construction5.5/100.5/10
Space & placement6.5/101.0/10
Light & reflections6.5/101.5/10
Purposeful detail5.5/101.0/10
Artistry & character6.5/101.5/10
Materials & effects6.0/100.5/10
Visual integrity7.0/103.0/10

Beach

Different prompts

GPT 6.1 Sol76.3/100

GPT 6.1 Sol: Beach SVG benchmark
Researcher observations

A cohesive sunset palette, sweeping shoreline and framing palm create an appealing beach illustration. Animals, birds, play and a prominent sun reflection fulfill the brief. Connected but schematic figures and simplified dolphin anatomy limit construction; stepped reflections and mostly flat surfaces limit lighting and material depth. Small beach accessories remain readable and edges are clean.

Benchmark task

Create an SVG of a amazing beach scene. Sunset, animals, fun, birds, reflections

Mai Thinking 144.2/100

Mai Thinking 1: Beach SVG benchmark
Researcher observations

A coherent, cheerful beach scene with balanced placement, clean shapes and controlled sunset colours. Animals, birds and playful accessories are recognizable, but basic dolphin construction, weak grounding, schematic reflections and sparse material detail limit the drawing's accomplishment.

Benchmark task

Create an SVG of a amazing beach scene. Sunset, animals, fun, birds, reflections

Compare category scores
CategoryGPT 6.1 SolMai Thinking 1
Prompt & likeness8.5/106.0/10
Anatomy & construction7.5/104.0/10
Space & placement7.5/105.0/10
Light & reflections7.5/104.0/10
Purposeful detail7.5/104.5/10
Artistry & character7.0/104.0/10
Materials & effects7.0/103.5/10
Visual integrity8.5/104.5/10

Ground Truth

Same prompt

GPT 6.1 Sol66.7/100

GPT 6.1 Sol: Ground Truth SVG benchmark
Benchmark task

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.

Mai Thinking 11.8/100

Mai Thinking 1: Ground Truth SVG benchmark
Benchmark task

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.

Raccoon

Different prompts

GPT 6.1 Sol78.3/100

GPT 6.1 Sol: Raccoon SVG benchmark
Researcher observations

The masked raccoon rides the dog's back, and the dog's forepaw meets a handlebar connected to the deck. Expressive faces, a striped tail and sweeping wake create an appealing composition. Overlapping bodies compress the seating and rear-leg anatomy; hull depth and sunset illumination remain schematic.

Benchmark task

Generate an SVG: A raccoon sits on a dog's back while the dog steers a jet ski

Mai Thinking 137.3/100

Mai Thinking 1: Raccoon SVG benchmark
Researcher observations

The recognizable raccoon and clean, shaded forms make a readable cartoon. The dog's steering remains undemonstrated, while ambiguous seating contacts and a minimally constructed craft weaken the central interaction. Controlled gradients and edges deserve credit, but anatomy, purposeful detail and water displacement remain basic.

Benchmark task

SVG of a raccoon that sits on a dog's back while the dog steers a jet ski

Compare category scores
CategoryGPT 6.1 SolMai Thinking 1
Prompt & likeness8.5/104.0/10
Anatomy & construction7.5/102.5/10
Space & placement7.5/105.0/10
Light & reflections6.5/104.0/10
Purposeful detail8.0/103.5/10
Artistry & character8.5/103.5/10
Materials & effects7.5/104.0/10
Visual integrity8.5/106.0/10

Pelican

Different prompts

GPT 6.1 Sol79.0/100

GPT 6.1 Sol: Pelican SVG benchmark
Researcher observations

A clearly recognizable pelican rides a well-composed bicycle through a warm coastal scene. The expressive bill, restrained palette and carefully drawn wheels give the illustration character. Leg-to-pedal connections are less convincing, especially the obscured far foot. Lighting provides gentle volume but little directional shadow. The small subtitle is clipped at the lower border.

Benchmark task

Generate an SVG of a pelican riding a bicycle

Mai Thinking 156.5/100

Mai Thinking 1: Pelican SVG benchmark
Researcher observations

A recognizable pelican and bicycle combine clean rounded forms, expressive facial details and effective surface shading. Aligned wheels and soft shadows establish placement, but unresolved pedal engagement, absent steering contact and sparse drivetrain construction weaken the riding action. Limited feather complexity and shallow space constrain an otherwise appealing illustration.

Benchmark task

Generate an SVG of a pelican riding a bicycle

Compare category scores
CategoryGPT 6.1 SolMai Thinking 1
Prompt & likeness9.0/107.0/10
Anatomy & construction7.0/104.5/10
Space & placement8.0/105.5/10
Light & reflections7.0/107.0/10
Purposeful detail8.0/105.0/10
Artistry & character8.5/105.0/10
Materials & effects7.5/104.5/10
Visual integrity8.0/107.0/10