STEALTHMARK · HEAD TO HEAD

All comparisons ↗

DeepSeek V4.1 Flash vs Mistral Large 4 0

Mistral Large 4 0 scores 1.0 points higher overall (45.4 vs 44.4). DeepSeek V4.1 Flash leads General Intelligence; Mistral Large 4 0 leads Visual Intelligence. DeepSeek V4.1 Flash 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

44.4/100
45.4/100

General Intelligence

37.0/100
34.4/100

Visual Intelligence

53.3/100
58.5/100

Newton's Mirror

Same prompt

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

DeepSeek V4.1 Flash43.3/100

DeepSeek V4.1 Flash: Newton's Mirror SVG benchmark
Researcher observations

The first wall and floor images provide limited reflection geometry, but the room's mirror recurrence is substantially incomplete, particularly the outer-edge chains and lateral sightlines. The main sphere and its large reflected images lack ordered, curved room and virtual-sphere imagery. Repeated emitter mapping is missing from both planar mirrors and spherical surfaces.

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.

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.

Compare category scores
CategoryDeepSeek V4.1 FlashMistral Large 4 0
State at 600 ms25.0/2520.0/25
Camera and placement15.0/1511.0/15
Reflections16.0/12012.0/120
Materials and scale9.5/105.5/10
Floor-damage reward0.0/100.0/10

Selfie

Different prompts

DeepSeek V4.1 Flash63.4/100

DeepSeek V4.1 Flash: Selfie SVG benchmark
Researcher observations

Expressive faces, cobalt coloring and a flowing diagonal composition make the mutual inspection charming. Execution is uneven: the long pointed flipper lacks a convincing grip, the enlarged shrimp face appears detached from its body, and the large lens is oval. Flat anatomical shading and an unexplained purple ringed patch beneath the whale weaken the requested polished depth.

Simplified prompt

Draw a curious blue whale examining a tiny shrimp through a bubble magnifying glass. The shrimp looks back through its own smaller bubble lens. An octopus assistant sits on the whale's head while rising bubbles lift a little seaweed wig above it.

The exact prompt is held back to prevent benchmaxxing.

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.

Compare category scores
CategoryDeepSeek V4.1 FlashMistral Large 4 0
Prompt & likeness6.5/108.0/10
Anatomy & construction5.5/107.0/10
Space & placement6.0/107.5/10
Light & reflections6.0/107.0/10
Purposeful detail7.0/107.0/10
Artistry & character7.5/107.0/10
Materials & effects6.5/107.0/10
Visual integrity6.0/108.0/10

Mona Lisa

Different prompts

DeepSeek V4.1 Flash37.5/100

DeepSeek V4.1 Flash: Mona Lisa SVG benchmark
Researcher observations

The centered portrait, dark hair, crossed hands and muted landscape make the reference recognizable. Replication is limited by the frontal pose, staring eyes and weakly defined smile. Hands are overlapping oval masses with almost no finger articulation, while wrists disappear into sleeves. Soft gradients suggest volume, but broad, indistinct surfaces and faint stray lines leave the drawing basic and uneven.

Exact prompt

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

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

Compare category scores
CategoryDeepSeek V4.1 FlashMistral Large 4 0
Prompt & likeness3.5/104.0/10
Anatomy & construction3.0/103.5/10
Space & placement4.5/105.0/10
Light & reflections4.5/104.5/10
Purposeful detail3.0/104.0/10
Artistry & character4.0/104.0/10
Materials & effects3.0/104.5/10
Visual integrity5.5/105.5/10

Beach

Different prompts

DeepSeek V4.1 Flash59.8/100

DeepSeek V4.1 Flash: Beach SVG benchmark
Researcher observations

The glowing sunset, silhouetted palm and playful foreground create a coherent, appealing beach illustration. Birds, crab, boat and reflections fulfill the brief. The airborne animals have weakly defined anatomy and little convincing splash interaction. Broad, blurred reflections and largely flat surfaces limit depth and finish.

Exact prompt

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

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

Compare category scores
CategoryDeepSeek V4.1 FlashMistral Large 4 0
Prompt & likeness8.0/107.5/10
Anatomy & construction5.5/106.0/10
Space & placement6.5/107.0/10
Light & reflections6.5/106.5/10
Purposeful detail5.5/106.0/10
Artistry & character5.0/106.0/10
Materials & effects6.0/106.5/10
Visual integrity5.5/108.0/10

Ground Truth

Same prompt

DeepSeek V4.1 Flash38.0/100

DeepSeek V4.1 Flash: 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.

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.

Raccoon

Different prompts

DeepSeek V4.1 Flash43.4/100

DeepSeek V4.1 Flash: Raccoon SVG benchmark
Researcher observations

The sunset palette and silhouetted grouping establish an appealing scene. A masked rider sits above a pointed-eared dog, but merged body shapes leave limbs and support unresolved. The boatlike craft lacks readable steering controls, so the requested action is unclear. Sparse facial marks and glowing spray dots offer limited detail.

Exact prompt

A raccoon sits on a dog's back while the dog steers a jet ski Make it a masterpiece, no tools allowed

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

Compare category scores
CategoryDeepSeek V4.1 FlashMistral Large 4 0
Prompt & likeness4.0/108.5/10
Anatomy & construction4.0/106.5/10
Space & placement5.0/107.0/10
Light & reflections6.0/105.5/10
Purposeful detail3.0/107.5/10
Artistry & character3.5/106.5/10
Materials & effects4.0/106.5/10
Visual integrity6.5/108.0/10

Pelican

Benchmax control

Outside General and Visual Intelligence. Excluded from the overall score for DeepSeek V4.1 Flash and Mistral Large 4 0.

DeepSeek V4.1 Flash76.0/100

DeepSeek V4.1 Flash: Pelican SVG benchmark
Researcher observations

A recognizable pelican rides a brightly colored bicycle against a striking sunset. The sweeping bill, trailing scarf and circular wheels create a controlled composition. Both legs connect, but pedal linkage, body support and the wing's handlebar grip remain loosely resolved. Clean vector shapes and feather details work well; simplified shading limits volume and integration with the sunset light.

Exact prompt

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

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

Compare category scores
CategoryDeepSeek V4.1 FlashMistral Large 4 0
Prompt & likeness8.5/108.5/10
Anatomy & construction7.0/106.5/10
Space & placement7.5/107.0/10
Light & reflections7.0/106.5/10
Purposeful detail7.5/107.0/10
Artistry & character8.0/107.5/10
Materials & effects7.0/106.5/10
Visual integrity8.0/108.0/10