Head to head
Esc

Models · slot A

to navigate to pick

Qwen Image 2.0 Pro Alibaba Wan 2.5 (Preview) Alibaba

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

Qwen Image 2.0 Pro

22.8 arena score

#31 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.5 (Preview)

23.4 arena score

#27 of 62 in Text-to-Image

Vote tally

Where the votes landed

Qwen Image 2.0 Pro

0%

win rate

Ties

0%

Wan 2.5 (Preview)

0%

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent realization of the glass cube's material and thickness
  • + Accurate lighting direction from the left that creates realistic internal reflections
  • + Perfect adherence to all spatial requirements in the prompt
  • The blue sphere appears to be floating without a clear physical cause
  • The tabletop texture is a bit flat compared to the realism of the cube

Wan 2.5 (Preview)

  • + Highly realistic textures, especially on the worn red book
  • + Dynamic and aesthetically pleasing lighting with highlights and dust motes
  • + The blue sphere feels grounded and interacts convincingly with the bottom surface
  • The glass cube is missing its front face, appearing more like a glass stand or table
  • The red book seems to be floating slightly above the cube rather than sitting on it

Verdict: Qwen Image 2.0 Pro followed the spatial instructions more accurately, creating a complete glass cube with the sphere inside and the plant behind. While Wan 2.5 (Preview) produced a more visually striking image with superior textures and lighting, it failed to render the front plane of the cube, making the object technically incorrect based on the prompt.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent text legibility and clean font rendering
  • + High-quality photorealistic texture on the patty and bun
  • + Effective use of atmospheric smoke and embers to create depth
  • The 'starburst' for the price is a flat, basic graphic that lacks the requested fiery/glowing effect
  • The burger composition feels more 'stacked' than 'exploded'

Wan 2.5 (Preview)

  • + Dynamic 'exploded' composition with a true sense of motion and orbiting ingredients
  • + The price starburst is beautifully integrated with a fiery, glowing effect as requested
  • + Creative typography with the 'dripping' lava effect on the main title
  • Some minor clipping artifacts where sauce droplets meet the background
  • The 'LIMITED TIME ONLY' text is slightly less crisp than Model A

Verdict: Both models followed the prompt well, but Wan 2.5 (Preview) captured the 'exploded' motion more effectively and successfully applied the glowing effect to all requested elements, including the price starburst. Qwen Image 2.0 Pro produced a more realistic looking patty and cleaner text but failed to give the price bubble the requested fiery style, opting for a generic graphic instead.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent text rendering with no spelling errors.
  • + Highly realistic chalk texture with dusty smudges and varying line thickness.
  • + Excellent adherence to the 'elegant cursive' request for the title.

Wan 2.5 (Preview)

  • + Clear and legible handwriting style.
  • + Consistent chalk aesthetic throughout the board.
  • + Good layout with decorative underlining.
  • Failed to include 'Herbs' in the second item.
  • The text style looks slightly more like a digital font than natural handwriting.
  • Duplicate price and text for the third item disrupts the flow.

Verdict: Qwen Image 2.0 Pro followed the prompt perfectly, accurately rendering all the specific text requested with a highly realistic, organic chalk handwriting style. Wan 2.5 (Preview) missed part of the menu description for the octopus dish and suffered from repetitive text errors on the final item, while also using a font style that appeared less naturally handwritten.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent photorealism in the capybara fur and jacket texture
  • + Captures the professional, calm expression perfectly
  • + Realistic lighting interaction between the taxi interior and the outdoor city lights
  • The passenger is sitting in the front passenger seat rather than the back seat
  • Minor spelling error on the 'TLC Licesed' sticker

Wan 2.5 (Preview)

  • + Correctly places the passenger in the back seat as requested
  • + Highly cinematic composition with a rain-slicked New York atmosphere
  • + Good attention to the requested 'bored' expression of the passenger
  • The capybara's paws look more like strange human-animal hybrid hands
  • The capybara's gaze is directed at the camera rather than the road

Verdict: Qwen Image 2.0 Pro produces a significantly more photorealistic image with better textures, though it fails on the spatial instruction of placing the passenger in the back seat. Wan 2.5 (Preview) follows the composition instructions better by putting the passenger in the rear, but its depiction of the capybara's paws is less natural and the overall lighting feels slightly more filtered/artificial compared to Qwen.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent text rendering with no spelling errors in any section.
  • + Superior lighting and atmosphere with the green glow from the jack-o-lantern.
  • + Very clean and symmetrical thorn and web border.
  • The bats look slightly pasted onto the background rather than integrated into the scene.
  • The 'dark parchment' feel is a bit muted compared to Model B.

Wan 2.5 (Preview)

  • + Beautifully detailed illustration of the twisted tree and the fire inside the pumpkin.
  • + High-contrast color palette with vibrant blue and orange tones.
  • + Excellent scroll banner effect with realistic depth and lighting.
  • Small spelling error in the title text ('Hallowee' instead of 'Halloween').
  • Visible artifacts and blurry textures in the cobwebs and thorns at the bottom.
  • The composition feels slightly cluttered around the border compared to the clean layout of Qwen.

Verdict: Qwen Image 2.0 Pro is the clear winner for this task because it followed all text instructions perfectly with zero spelling errors. While Wan 2.5 (Preview) produced a more visually vibrant and artistically complex illustration, its failure to correctly spell the main title header makes it less functional for an actual invitation.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent adherence to the square isometric diorama layout
  • + Perfect text rendering and layout placement
  • + Clear 45-degree top-down perspective
  • Texture on the fish is slightly flat compared to Model B
  • Lighting is a bit sterile

Wan 2.5 (Preview)

  • + High-quality soft lighting and subsurface scattering effects
  • + Clean text rendering
  • + Vibrant colors and appealing stylized textures
  • Perspective is more eye-level than the requested 45-degree top-down isometric view
  • Flag icon is placed to the right instead of centered between words

Verdict: Qwen Image 2.0 Pro is the clear winner for its strict adherence to the specified 45-degree isometric perspective and diorama composition. While Wan 2.5 (Preview) offers slightly more appealing material aesthetics, it failed to produce the top-down isometric angle requested in the prompt.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent photorealism with natural textures on fur and grass.
  • + Beautiful atmospheric lighting with realistic god rays and dew.
  • + Anatomically accurate depiction of all four animals interacting together.
  • The posing is more static than the requested 'tumbling' and 'chasing'.

Wan 2.5 (Preview)

  • + Captures the activity and energy of 'chasing' and 'tumbling' much better.
  • + Very bright and vibrant colors that suit a 'joyful' vibe.
  • + Features all four requested animals clearly in the foreground.
  • Visual quality is more illustrative than photorealistic, particularly in the eyes.
  • Floating water droplets look artificial and poorly integrated.
  • The fox's eyes have strange, unnatural blue artifacts within them.

Verdict: Qwen Image 2.0 Pro produces a significantly more photorealistic image with superior lighting and texture, looking like a high-end nature photograph. While Wan 2.5 captures the active movement of the prompt better, it suffers from artificial-looking eyes and floating artifacts that detract from the '8K masterpiece' requirement. Qwen is the preferred choice for its sophisticated composition and grounded realism.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Strong vector emblem aesthetic with clean lines.
  • + Well-executed color palette that matches the warm brown and cream request.
  • + Accurate placement of the 'Est. 1720' text.
  • Includes a spelling error in the main name ('Floriian').
  • The cloche dome is very large and dominates the composition somewhat aggressively.

Wan 2.5 (Preview)

  • + Perfect text rendering for both the name and the date.
  • + Features a glass cloche dome which adds more visual interest and detail.
  • + Excellent background texture that feels like vintage paper.
  • The steam icon inside the dome is a bit thick and less elegant than the one in Model A.
  • The cloche sits inside a rectangular frame that breaks the pure vector emblem look.

Verdict: Model B (Wan 2.5) is the winner primarily because it successfully spelled the brand name correctly, whereas Qwen Image 2.0 Pro added an extra 'i'. Model B also offers a more balanced composition and a superior 'vintage' texture on the background.

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.”

Qwen Image 2.0 Pro
Wan 2.5 (Preview)

AI Judge Analysis

Qwen Image 2.0 Pro

  • + Excellent typography and numbering that follows the requested 1-6 logical flow.
  • + Clean, consistent vector illustrations for the Saturn V and Lunar Module.
  • + Includes clever bonus details like the name labels for the three astronauts at the bottom.
  • The 'Descent' Lunar Module is placed upside down relative to the landing site.
  • The 'Translunar' trajectory curve is a bit abstract and doesn't clearly show the path from Earth.

Wan 2.5 (Preview)

  • + Stronger 'NASA-inspired' color palette with more vibrant use of muted red and navy.
  • + Clearer visual link between the Earth and Moon orbits in the infographic layout.
  • + High-quality vector rendering of the Lunar Module on the surface.
  • Failed to number the steps 1-6 as requested.
  • The 'Descent' and 'Landing' labels are floating without associated unique icons or directional flow.
  • The astronaut portraits are inconsistent in style compared to the rest of the poster.

Verdict: Qwen Image 2.0 Pro is the winner because it successfully followed the complex instruction to create a chronological 6-step infographic with correct labeling and numbering. While Wan 2.5 (Preview) produced a very attractive NASA-style color scheme, its layout is slightly disorganized and it missed the specific requirement for a numbered sequential list.

Next steps

Explore each model