STEALTHMARK · HEAD TO HEAD

All comparisons ↗

Mistral Large 4 0 vs Muse Spark 1.3

Mistral Large 4 0 scores 12.4 points higher overall (45.4 vs 33.0). Mistral Large 4 0 scores higher on Newton's Mirror, with its largest category advantage in state at 600 ms.

See the difference ↘
All results ↗
All results ↗

Overall StealthMark

45.4/100
33.0/100

General Intelligence

34.4/100
23.9/100

Visual Intelligence

58.5/100
43.8/100

Newton's Mirror

Same prompt

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

Mistral Large 4 030.2/100

Mistral Large 4 0: Newton's Mirror SVG benchmark
Researcher observations

The central sphere, airborne black and deformed crimson support substantial state and placement credit. Recent cyan contact and crimson transport remain uncertain. Sparse wall patches and glossy gradients provide little evidence of the required extensive mirror system, while the missing centerline lamp and bulky crimson remain visible weaknesses.

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.

Muse Spark 1.319.7/100

Muse Spark 1.3: Newton's Mirror SVG benchmark
Researcher observations

The paint state is incorrectly and poorly drawn, despite a recognizable sphere-and-paint setup. The oversized sphere, oversized compact paint bodies, and blurred wall and floor images further limit the result. Isolated reflection cues provide very little support for the required repeated virtual rooms, nested spherical imagery or emitter mapping.

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
CategoryMistral Large 4 0Muse Spark 1.3
State at 600 ms20.0/2512.5/25
Camera and placement11.0/158.5/15
Reflections12.0/1205.5/120
Materials and scale5.5/104.0/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

Mistral Large 4 072.5/100

Mistral Large 4 0: Selfie SVG benchmark
Researcher observations

An appealing, coherent illustration whose enormous rounded cat anchors the windblown composition. Warm shading and floating sketches communicate the brief well. Simplified paws, faint ear construction, inconsistent wind cues and limited material texture keep the execution below exceptional.

Prompt withheld

The exact prompt is held back to prevent benchmaxxing.

Muse Spark 1.372.8/100

Muse Spark 1.3: Selfie SVG benchmark
Researcher observations

The luminous creature and geometric mirror counterpart communicate self-recognition through a coherent palette and expressive eyes. The transformed reflection is purposeful. Simple oval anatomy, ambiguous reaching-arm construction, shallow spatial staging and limited illumination of nearby surfaces keep the illustration below exceptional execution.

Simplified prompt

Imagine yourself as an AI creature looking at its reflection. Choose a creature and setting that express how you see yourself. The reflection can match you or show a different side of your identity.

The exact prompt is held back to prevent benchmaxxing.

Compare category scores
CategoryMistral Large 4 0Muse Spark 1.3
Prompt & likeness8.0/108.5/10
Anatomy & construction7.0/107.0/10
Space & placement7.5/107.0/10
Light & reflections7.0/107.0/10
Purposeful detail7.0/107.5/10
Artistry & character7.0/106.5/10
Materials & effects7.0/107.0/10
Visual integrity8.0/108.0/10

Mona Lisa

Different prompts

Mistral Large 4 041.7/100

Mistral Large 4 0: Mona Lisa SVG benchmark
Researcher observations

A recognizable, cleanly rendered interpretation with a restrained palette and some facial modeling. Its enlarged frontal head, simplified expression, compressed low hands and schematic landscape substantially limit likeness and construction. The smooth rendering does not reproduce the painting's nuanced anatomy, clothing or atmospheric depth.

Exact prompt

Generate an SVG of mona-lisa Make it a masterpiece You may NOT use tools, browser, image analysis. Directly output the SVG as code

Muse Spark 1.315.0/100

Muse Spark 1.3: Mona Lisa SVG benchmark
Researcher observations

Dark hair, a restrained smile and overlapping hands suggest Mona Lisa, but replication is weak. The face is markedly elongated, the hands are oval pads with faint finger strokes, and the atmospheric landscape is absent. Soft gradients provide basic volume, while the frontal symmetry, shallow space and sparse clothing detail limit the portrait’s drawing quality.

Exact prompt

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

Compare category scores
CategoryMistral Large 4 0Muse Spark 1.3
Prompt & likeness4.0/101.0/10
Anatomy & construction3.5/101.5/10
Space & placement5.0/101.5/10
Light & reflections4.5/101.5/10
Purposeful detail4.0/101.0/10
Artistry & character4.0/101.5/10
Materials & effects4.5/101.5/10
Visual integrity5.5/103.0/10

Beach

Different prompts

Mistral Large 4 065.4/100

Mistral Large 4 0: Beach SVG benchmark
Researcher observations

A clean, appealing beach illustration with clear subject coverage, a cohesive sunset palette and expressive animal details. Bodies and accessories resolve basic construction coherently, although joints remain schematic. Layered shapes establish modest depth; generic oval shadows and flat surfaces limit physical richness. Repeated forms and sparse articulation leave room for more accomplished drawing.

Exact prompt

Create an SVG of a amazing beach scene. Sunset, animals, fun, birds, reflections Make it a masterpiece You may NOT use tools, browser, image analysis. Directly output the SVG as code

Muse Spark 1.344.8/100

Muse Spark 1.3: Beach SVG benchmark
Researcher observations

The warm sunset, framing palms and colorful beach accessories create an appealing scene with the requested animals, birds and reflections. Construction remains schematic: the raised hand misses the kite string, and a doglike silhouette hangs above the water without clear support. The sun reflection establishes a focal path, but shadows and materials lack depth. An unexplained horizontal bar crosses the sun.

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
CategoryMistral Large 4 0Muse Spark 1.3
Prompt & likeness7.5/106.5/10
Anatomy & construction6.0/103.0/10
Space & placement7.0/105.5/10
Light & reflections6.5/106.5/10
Purposeful detail6.0/105.0/10
Artistry & character6.0/103.5/10
Materials & effects6.5/103.0/10
Visual integrity8.0/103.5/10

Ground Truth

Same prompt

Mistral Large 4 035.6/100

Mistral Large 4 0: 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.

Muse Spark 1.326.4/100

Muse Spark 1.3: 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

Different prompts

Mistral Large 4 069.5/100

Mistral Large 4 0: Raccoon SVG benchmark
Researcher observations

The central interaction is clear, with recognizable animals, expressive faces and a coherent sunset composition. Clean contours and readable accessories give the cartoon polish. Simplified joints, uncertain steering attachment, shallow hull volume and limited directional lighting constrain its physical resolution.

Exact prompt

SVG of a raccoon that sits on a dog's back while the dog steers a jet ski Make it a masterpiece You may NOT use tools, browser, image analysis. Directly output the SVG as code

Muse Spark 1.366.0/100

Muse Spark 1.3: Raccoon SVG benchmark
Researcher observations

The raccoon clearly rides on the dog's back, and the dog's paws reach the jet ski controls. Expressive faces and bright colors make the scene appealing. Simplified joints, crowded steering geometry and shallow hull perspective limit construction. The sun has no corresponding water reflection, and the splash shapes convey speed more clearly than convincing displacement.

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
CategoryMistral Large 4 0Muse Spark 1.3
Prompt & likeness8.5/108.5/10
Anatomy & construction6.5/106.5/10
Space & placement7.0/107.0/10
Light & reflections5.5/105.0/10
Purposeful detail7.5/106.5/10
Artistry & character6.5/106.0/10
Materials & effects6.5/106.0/10
Visual integrity8.0/107.5/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for Mistral Large 4 0 and Muse Spark 1.3.

Mistral Large 4 072.3/100

Mistral Large 4 0: Pelican SVG benchmark
Researcher observations

A coherent, appealing pelican illustration with a continuous body silhouette, readable bicycle and grounded wheels. Simplified legs and ambiguous steering and pedal connections limit construction. Clean shapes and expressive accessories succeed, while shallow depth, modest lighting and sparse material differentiation leave substantial room for refinement.

Exact prompt

Generate an SVG of a pelican riding a bicycle Make it a masterpiece You may NOT use tools, browser, image analysis. Directly output the SVG as code

Muse Spark 1.372.0/100

Muse Spark 1.3: Pelican SVG benchmark
Researcher observations

The pelican and bicycle are immediately recognizable, with an expressive face, bold bill and cheerful composition. Both legs connect to the body and reach pedal-like supports, but articulation, saddle support and wing contact with the handlebar remain unclear. Wheel alignment and layering are coherent. Simple landscape shapes, generic shadows and limited material variation constrain the finish.

Exact prompt

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

Compare category scores
CategoryMistral Large 4 0Muse Spark 1.3
Prompt & likeness8.5/109.0/10
Anatomy & construction6.5/106.5/10
Space & placement7.0/107.0/10
Light & reflections6.5/106.0/10
Purposeful detail7.0/107.0/10
Artistry & character7.5/107.5/10
Materials & effects6.5/106.5/10
Visual integrity8.0/107.5/10