GPT Image 2 OpenAI Qwen Image 2.0 Pro Alibaba

Settled by community votes across 9 shared challenges, with an AI judge weighing in on each.

GPT Image 2

28.1 arena score

#3 of 62 in Text-to-Image

Top 3 in Text-to-Image

Skill signature · Text-to-Image

Qwen Image 2.0 Pro

22.5 arena score

#32 of 62 in Text-to-Image

Vote tally

Where the votes landed

GPT Image 2

win rate

Ties

Qwen Image 2.0 Pro

win rate

Shared challenges 9

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Geometric Composition

Text-to-Image

“A glass cube on a wooden table. Inside the cube is a small blue sphere. On top of the cube sits a red book. A green plant is behind the cube, partially visible through the glass. Soft window light from the left.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent realism in the glass refraction and thickness.
+ Accurate lighting coming from the window on the left.
+ The blue sphere rests naturally on the bottom surface.

− The plant is slightly less 'behind' and more to the side compared to Model B.

Qwen Image 2.0 Pro

+ Successfully positions the plant directly behind the cube as requested.
+ Good texture on the wooden table surface.

− The blue sphere is floating inexplicably in the center of the cube.
− The back-left edge of the cube has a strange reflective error that looks like a solid mirror rather than glass.
− The glass lacks the realistic thickness and internal reflections seen in Model A.

Verdict: GPT Image 2 is the superior image because it handles physics and optical properties realistically, showing a blue sphere resting on the cube's floor with convincing glass refraction. Qwen Image 2.0 Pro fails on basic physics by having the sphere float and contains a jarring visual artifact on the left side of the cube that looks like a mirror.

Magic Burger Explosion: Fiery Photorealism Challenge

Text-to-Image

“Ad for 'Magic Burger'. Dynamic, exploded burger with all components (bun, patty, cheese, lettuce, tomato, sauce) suspended in mid-air. Emphasize photorealistic detail and a sense of motion. Dark, fiery background with glowing embers. Integrate text: 'MAGIC BURGER' as a prominent title, 'LIMITED TIME ONLY' as a secondary message, and '€6.99' in a starburst, all rendered with a fiery, glowing effect.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent photorealistic texture on the burger patty and buns.
+ High-energy composition with dynamic movement and splashing sauce.
+ Perfect adherence to the fiery, glowing effect for all text elements.

− The composition is a bit crowded with the large text and starburst overlapping the background elements.

Qwen Image 2.0 Pro

+ Clean, symmetrical layout that works well for a commercial advertisement.
+ Good legibility of all requested text components.
+ Effective use of atmospheric smoke and subtle embers.

− The starburst element is a flat graphic that doesn't match the requested fiery, glowing style.
− The lighting on the burger feels a bit static compared to the 'dynamic' prompt requirement.

Verdict: GPT Image 2 captured the energy and 'fiery' style of the prompt more effectively, particularly with the glowing text and the highly detailed, messy texture of the burger components. Qwen Image 2.0 Pro produced a cleaner layout, but failed to integrate the price starburst into the fiery aesthetic, making it look like a separate clip-art element.

Chalkboard Menu

Text-to-Image

“Handwritten-style chalkboard menu in a cozy café, all text rendered in the exact same realistic chalk handwriting style with natural variations in letter size, slight slant, and chalk texture — no printed or digital fonts anywhere on the board. Title at the top in elegant cursive chalk handwriting: ‘TODAY’S SPECIALS – APRIL 30, 2026’. Below it, three menu items also in the same handwritten chalk style: ‘Truffle Mushroom Risotto – $24’, ‘Grilled Octopus with Lemon & Herbs – $28’, ‘Brown Butter Chocolate Chip Cookies – $9’. At the very bottom, smaller text in the identical handwritten chalk style (slightly smaller but still clearly legible with the same handwriting characteristics): ‘All items made fresh daily • Ask about our gluten-free options’. Warm ambient café lighting, visible chalk dust and smudges, realistic handwriting imperfections, no clean printed text anywhere.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent chalk texture with realistic dusty edges and letter variations.
+ Perfect adherence to the full menu list and pricing requested.
+ Coherent and warm café environment with a well-framed wooden board.

− The cursive in the header is a bit stiff compared to professional chalk art.

Qwen Image 2.0 Pro

+ Clear and legible handwriting with good layout balance.
+ Strong chalk smudge effects that add to the realism of a used board.
+ Accurately rendered all requested text without spelling errors.

− The letter texture looks slightly more like a digital paint brush than dry chalk.
− The composition is at a sharp angle, making the text slightly harder to read than a straight-on shot.

Verdict: Both models followed the complex text prompt perfectly, with no spelling errors even in the long menu items. GPT Image 2 (Model A) is the winner because the chalk texture is significantly more realistic, capturing the grainy, dusty essence of physical chalk on slate better than Qwen Image 2.0 Pro (Model B), which has a smoother, more digital appearances.

The Capybara Taxi Driver

Text-to-Image

“Photorealistic scene inside a yellow New York taxi at night. A capybara is driving, wearing a yellow taxi driver cap and a dark jacket. It has a calm, professional expression and both front paws on the steering wheel. In the back seat sits a human businesswoman in a coat, looking at her phone with a completely normal, bored expression (as if this is just another normal ride). Through the windows you can see the streets of Manhattan at night with blurred lights. Realistic taxi interior, photorealistic, detailed fur and fabric, 35mm lens, night lighting with reflections, shallow depth of field.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Captures a very cinematic, moody lighting style consistent with a night taxi
+ Excellent depth of field with realistic background bokeh
+ Highly detailed fur texture and plausible capybara anatomy

− Composition is tight and crops out most of the cab's interior details
− The capybara's left paw is somewhat indistinct on the wheel

Qwen Image 2.0 Pro

+ Includes more environmental details like the TLC license plate and dashboard
+ The passenger's expression and action perfectly match the 'bored businesswoman' prompt
+ Shows both paws clearly on the steering wheel as requested

− Visible spelling error on the dashboard sticker ('Licesed')
− The lighting is slightly flat and looks less like a single photorealistic shot

Verdict: GPT Image 2 offers superior aesthetic quality and lighting, creating a more believable cinematic scene. However, Qwen Image 2.0 Pro followed the specific compositional requirements more closely, including small details like the TLC license and a clearer view of both paws on the wheel. GPT Image 2 is generally preferred for its visual realism despite the tighter crop.

The Halloween Invitation

Text-to-Image

“Vintage gothic Halloween party invitation. Dark parchment poster, spooky border with webs and thorns, central glowing jack-o-lantern, bats, twisted trees, moody night sky. Add elegant gothic title text saying "Halloween Party Invitation", a small scroll banner saying "You are invited to a night of frights", and event details at the bottom: Date: 30.10.2026 Time: 7pm Location: The Arches, NYC Spooky but polished, cinematic lighting, square format.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent typography with a perfect vintage gothic aesthetic
+ Complex and detailed composition featuring a custom NYC backdrop in the architecture
+ Perfectly captures the parchment texture and cinematic lighting requested

− The '3' in the date is slightly stylized but still legible

Qwen Image 2.0 Pro

+ Creative use of green lighting for the jack-o-lantern
+ Clean and legible text layout
+ Good adherence to specific elements like the border of webs and thorns

− The digital art style feels more modern than the requested 'vintage' and 'parchment' look
− Bats have visible artifacts/clipping issues near the wings
− The 'Halloween' text is slightly off-center

Verdict: GPT Image 2 perfectly captures the requested vintage gothic mood with sophisticated typography and a high level of background detail, including clever references to the NYC location. Qwen Image 2.0 Pro is colorful and meets all prompt requirements but leans too much into a clean, modern digital illustration style rather than the dark parchment poster aesthetic requested.

Isometric Miniature Diorama Scenes

Text-to-Image

“Create a clear, 45° top-down isometric miniature 3D cartoon scene of Japan's signature dish: sushi, with soft refined textures, realistic PBR materials, gentle lighting, on a small raised diorama base with minimal garnish and plate. Solid light blue background. At top-center: 'JAPAN' in large bold text, 'SUSHI' below it, small flag icon. Perfectly centered, ultra-clean, high-clarity, square format.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent PBR textures and lighting that create a premium 3D look.
+ Great attention to detail with the miniature dioroma elements like the stone lantern and bamboo leaves.
+ Strong typography with stylistic 3D effects that match the scene context.

− The scene is busier than the requested 'minimal garnish' requirement.
− Includes extra elements like chopsticks and a soy sauce dish not explicitly requested.

Qwen Image 2.0 Pro

+ Perfect adherence to the 'minimal garnish' and 'small raised diorama base' instructions.
+ Very clean and accurate isometric perspective.
+ Text layout is precisely centered as requested.

− The textures are very flat and lack the 'realistic PBR' quality requested.
− The typography is plain and lacks the visual polish seen in the other model.
− The overall image looks a bit simplified and less like a high-end 3D render.

Verdict: GPT Image 2 is the superior image due to its exceptional material quality and lighting, which perfectly capture the 'soft refined textures' and 'realistic PBR' aspect of the prompt. While Qwen Image 2.0 Pro followed the instruction for a 'minimal' setup more closely, it failed to deliver the high-clarity 3D aesthetic that GPT Image 2 achieved.

Adorable Baby Animals in Sunny Meadow

Text-to-Image

“Hyper-photorealistic scene of fluffy baby animals—a golden retriever puppy, tabby kitten, baby bunny, and red fox kit—with big expressive eyes and ultra-detailed soft fur, playfully chasing butterflies and tumbling together in a lush wildflower meadow, warm golden sunrise light with god rays and dew sparkles, joyful wholesome vibe, 8K masterpiece.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent depiction of motion, with animals actively leaping and paws liftoff.
+ Strong lighting effect with beautiful backlighting on the fur and clear god rays.
+ Perfect adherence to all four specific animals while maintaining individual character.

− Some digital artifacts on the edges of the butterflies.
− The background butterflies are a bit blurry compared to the foreground subjects.

Qwen Image 2.0 Pro

+ Beautiful, realistic wildflowers that add to the composition.
+ Soft, natural rendering of the puppy's fur.
+ Convincing 'tumbling' interaction between the kitten, fox, and bunny.

− The fox kit has an unnaturally long, thick tail that looks more like a squirrel or raccoon tail.
− The god rays are a bit less integrated and look slightly like a filter overlay compared to the scene lighting.
− The kitten's anatomy feels a bit stiff in the center.

Verdict: GPT Image 2 is the winner as it captures the 'playfully chasing' aspect of the prompt with much more dynamic energy and superior lighting. While Qwen Image 2.0 Pro has lovely floral details, the fox kit's tail is anatomically incorrect and the composition feels more static than the joyful romp depicted in GPT Image 2.

Vintage Cafe Logo

Text-to-Image

“Vintage minimalist restaurant logo for "Caffè Florian", retro cloche dome with steam and "Est. 1720" banner, classic typography, warm brown and cream tones, subtle texture on light background, vector emblem style.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent typography with correct spelling and sophisticated serif styling
+ Highly detailed engraving texture that fits the 'vintage' prompt perfectly
+ Superior composition with a balanced frame and elegant banner

− Steam effect is slightly disconnected from the cloche

Qwen Image 2.0 Pro

+ Adheres to the color palette and basic element requirements
+ Clean vector style

− Spelling error in the main text ('Floriian')
− Steam is placed awkwardly on top of the dome rather than rising from beneath
− Composition feels cramped and lacks the requested 'classic' elegance

Verdict: GPT Image 2 is significantly better, offering a professional-grade vintage emblem with perfect spelling and sophisticated line work. Qwen Image 2.0 Pro fails on core details, including a spelling error in the name and a less refined composition that feels amateur by comparison.

Apollo 11: Journey to Tranquility

Text-to-Image

“Create a clean, modern vector infographic poster about the Apollo 11 mission. NASA-inspired palette (navy, white, muted red, light gray). Flat-vector style, crisp lines, consistent iconography, subtle gradients only. Steps (stop at landing): 1. Launch (Saturn Vicon) 2. Earth Orbit (Earth + orbit ring icon) 3. Translunar (trajectory arc icon) 4. Lunar Orbit (Moon + orbit ring icon) 5. Descent (lunar module descending icon) 6. Landing (lunar module on the surface icon) Small supporting elements (minimal text): • Crew strip: three silhouette icons with only last names: Armstrong, Aldrin, Collins. • Landing site marker: Moon pin labeled "Tranquility" only. Layout constraints: generous margins, large readable labels, clean background with subtle stars. Vector-only, print-poster look, high resolution.”

GPT Image 2

Qwen Image 2.0 Pro

AI Judge Analysis

GPT Image 2

+ Excellent text rendering with clear, legible titles and labels.
+ Highly professional layout with a balanced grid and consistent borders.
+ Strong attention to detail in the icons and the inclusion of the NASA-style mission patch.

− The iconography leans more towards detailed illustration than true flat-vector style.
− The translunar trajectory icon shows a capsule rather than just a simple arc as requested.

Qwen Image 2.0 Pro

+ Successfully follows the request for a minimalistic flat-vector style.
+ Good use of vertical space to represent the chronological steps of the mission.
+ Accurate representation of the 'Tranquility' landing site with a simple pin.

− Lacks a main title for the infographic, making it feel less like a complete poster.
− Iconography is somewhat inconsistent in scale and placement relative to the labels.
− The crew icons at the bottom are very small and lacks the professional polish of the other model.

Verdict: GPT Image 2 is significantly more polished and better functions as a complete infographic poster, featuring excellent typography and a professional grid layout. While Qwen Image 2.0 Pro captures the 'flat vector' style more accurately, it fails to include a main title and feels less substantial as a design piece. GPT Image 2's inclusion of a mission patch and clear crew section makes it the superior choice for a thematic NASA poster.