STEALTHMARK · HEAD TO HEAD

All comparisons ↗

GPT 5.6 Terra vs Mai Thinking 1

GPT 5.6 Terra scores 23.8 points higher overall (43.3 vs 19.5). GPT 5.6 Terra scores higher on Ground Truth.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

43.3/100
19.5/100

General Intelligence

32.5/100
10.0/100

Visual Intelligence

56.2/100
30.8/100

Newton's Mirror

Same prompt

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

GPT 5.6 Terra27.1/100

GPT 5.6 Terra: Newton's Mirror SVG benchmark
Researcher observations

The real sphere and airborne black blob are substantially too low in the complete frame after accounting for aspect ratio. The first wall and floor reflections have incompatible placement, relative size or silhouette. Both lateral regions lack the references' receding lane-and-chain organization. The few recognizable mirror images provide limited optical structure. The main, side and floor spheres replace nested mirror imagery with smooth bands, while sparse planar light patches and broad spherical highlights fail to establish coherent repeated emitter mapping.

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 5.6 TerraMai Thinking 1
State at 600 ms23.5/257.5/25
Camera and placement6.0/153.5/15
Reflections7.0/1204.0/120
Materials and scale5.5/105.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

GPT 5.6 Terra70.9/100

GPT 5.6 Terra: Selfie SVG benchmark
Researcher observations

Six ivory heads and rounded lobes create a striking radial emblem around a clear hexagonal opening. Soft shading gives the bodies volume, but abrupt rectangular and diagonal band endings make the continuous alternating weave ambiguous. Repetitive scale lines and simplified faces convey an ornamental serpent more convincingly than living anatomy.

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 5.6 TerraMai Thinking 1
Prompt & likeness7.5/104.0/10
Anatomy & construction6.5/104.5/10
Space & placement7.5/105.0/10
Light & reflections7.5/104.5/10
Purposeful detail7.0/104.0/10
Artistry & character7.0/105.0/10
Materials & effects7.0/105.0/10
Visual integrity7.5/106.0/10

Mona Lisa

Different prompts

GPT 5.6 Terra38.0/100

GPT 5.6 Terra: Mona Lisa SVG benchmark
Researcher observations

The dark clothing, central portrait and restrained smile evoke the Mona Lisa, but replication is limited by the broad face, elongated neck, nearly frontal pose and indistinct landscape. Soft gradients give the face some volume. Crossed arms become rounded masses without readable fingers or wrists, and the expression lacks the original's subtlety. Clean framing and curves support an otherwise basic, uneven portrait.

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 5.6 TerraMai Thinking 1
Prompt & likeness4.0/101.0/10
Anatomy & construction3.0/100.5/10
Space & placement4.5/101.0/10
Light & reflections5.0/101.5/10
Purposeful detail3.0/101.0/10
Artistry & character3.5/101.5/10
Materials & effects3.0/100.5/10
Visual integrity5.5/103.0/10

Beach

Different prompts

GPT 5.6 Terra64.7/100

GPT 5.6 Terra: Beach SVG benchmark
Researcher observations

Warm sunset gradients, framing palms and colorful beach activities create an appealing scene. Animals, birds and a sun reflection fulfill the brief. The dog and turtle remain schematic, foreground depth is shallow, and the reflection forms rigid bands. Clean silhouettes and readable accessories support a competent illustration, but limited anatomy, material variation and lighting keep it below exceptional.

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 5.6 TerraMai Thinking 1
Prompt & likeness8.5/106.0/10
Anatomy & construction5.5/104.0/10
Space & placement7.0/105.0/10
Light & reflections6.0/104.0/10
Purposeful detail6.5/104.5/10
Artistry & character6.0/104.0/10
Materials & effects5.5/103.5/10
Visual integrity7.5/104.5/10

Ground Truth

Same prompt

GPT 5.6 Terra34.8/100

GPT 5.6 Terra: 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 5.6 Terra67.9/100

GPT 5.6 Terra: Raccoon SVG benchmark
Researcher observations

Expressive faces, a recognizable raccoon perched on the dog, and a sweeping wake make an appealing cartoon. The principal weakness is the steering interaction: the dog's paw sits beside the control assembly without a convincing handlebar grip. Bold outlines and coherent layering provide polish, while simplified shading, compressed seating geometry and angular splashes limit depth and physical credibility.

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 5.6 TerraMai Thinking 1
Prompt & likeness7.5/104.0/10
Anatomy & construction6.0/102.5/10
Space & placement7.5/105.0/10
Light & reflections6.5/104.0/10
Purposeful detail7.5/103.5/10
Artistry & character6.0/103.5/10
Materials & effects7.0/104.0/10
Visual integrity8.0/106.0/10

Pelican

Different prompts

GPT 5.6 Terra70.3/100

GPT 5.6 Terra: Pelican SVG benchmark
Researcher observations

The oversized bill, expressive eye and balanced twilight palette make the cyclist immediately readable. Clean contours and wheel details support the illustration, but the rabbit-like head tufts weaken pelican likeness. The wing does not clearly grip the handlebar, pedal contact is uneven, and the drivetrain is incomplete. Lighting remains mostly decorative.

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 5.6 TerraMai Thinking 1
Prompt & likeness8.0/107.0/10
Anatomy & construction6.5/104.5/10
Space & placement7.0/105.5/10
Light & reflections6.5/107.0/10
Purposeful detail6.5/105.0/10
Artistry & character7.0/105.0/10
Materials & effects6.5/104.5/10
Visual integrity8.0/107.0/10