Lumenfall Arena

Leaderboards

All leaderboards
Text-to-Image
Vote All Results
Image Editing
Vote All Results
Text-to-Video
Vote All Results
Image Upscaling
Vote All Results
Image-to-Video
Vote All Results
Text-to-Vector
Vote All Results
Head to head
Esc

Models · slot A

↑↓ to navigate ↵ to pick
Arena / Models / Alibaba

Alibaba

Model evolution · 2025 – 2026
Models
13
Challenges
29
Takes
195
Evolution oldest → newest · 13 versions

How Alibaba models have evolved

One model per node, oldest to newest, each with a sample of its work. These models do different jobs, like image, video, and upscaling, so the chip on each node names its mode. Compare versions within the same mode.

  1. 2025
    no take
    Qwen Image
    Aug 2025
  2. 2025
    no take
    Qwen Image Edit Latest
    Aug 2025
  3. 2025
    no take
    Qwen Image Edit 2509
    Sep 2025
  4. 2025
    no take
    Wan 2.5 (Preview)
    Sep 2025
  5. 2025
    Z-Image Turbo
    Text-to-Image
    Nov 2025
  6. 2025
    Wan 2.6
    Image Editing
    Dec 2025
  7. 2025
    Qwen Image Edit 2511
    Image Editing
    Dec 2025
  8. 2025
    Newest take
    Qwen Image Max
    Text-to-Image
    Dec 2025
  9. 2025
    Qwen Image 2512
    Text-to-Image
    Dec 2025
  10. 2026
    Newest take
    Qwen Image 2.0
    Text-to-Image
    Feb 2026
  11. 2026
    Qwen Image 2.0 Pro
    Text-to-Image
    Feb 2026
  12. 2026
    Wan 2.7
    Text-to-Image
    Apr 2026
  13. 2026
    Latest
    Wan 2.7 Pro
    Text-to-Image
    Apr 2026
Smarter every release 13 models

Intelligence over time

How Alibaba's models have grown more capable over time. Each point is one of their models at its release date and arena Elo, oldest to newest.

  • Qwen Image 2.0
  • Qwen Image 2.0 Pro
  • Qwen Image 2512
  • Qwen Image Max
  • Wan 2.6
  • Wan 2.7
  • Wan 2.7 Pro
  • Z-Image Turbo
Head to head

Every challenge, side by side

Each model's take on every challenge in this mode. Modes use different challenges and prompts, so pick one mode at a time; each view stands on its own.

Text-to-Image 17 Image Editing 10 Text-to-Video 1 Image-to-Video 1
Challenge 17 challenges ↓ · 8 models →
Z-Image Turbo
Nov 2025
Wan 2.6
Dec 2025
Qwen Image Max
Dec 2025
Qwen Image 2512
Dec 2025
Qwen Image 2.0
Feb 2026
Qwen Image 2.0 Pro
Feb 2026
Wan 2.7
Apr 2026
Wan 2.7 Pro
Apr 2026
Text-to-Image

The Capybara Taxi Driver

6/8 · 18 takes
Text-to-Image

The Capybara Taxi Driver

This challenge seems to be difficult for models because it mixes reality with fiction. Most models struggle to keep the taxi realistic or loose instructions like placing the passenger not in the backseat.

Prompt
“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.”
Judged on
  • Photorealistic
  • Realistic NYC taxi interior + night atmosphere
  • Positioning of passenger
  • Capybara wearing taxi driver cap
View full challenge
3
3
No entry yet
3
No entry yet
3
3
3
Text-to-Image

Chalkboard Menu

6/8 · 17 takes
Text-to-Image

Chalkboard Menu

This challenge forces models to use one consistent handwritten style across an entire dense menu instead of defaulting to clean printed text for the smaller details, a very common failure that reveals how well they actually understand and maintain stylistic coherence.

Prompt
“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.”
Judged on
  • Text Accuracy
  • Handwriting Consistency
  • Legibility
  • Chalk Realism
View full challenge
3
3
No entry yet
3
No entry yet
2
3
3
Text-to-Image

The Halloween Invitation

5/8 · 15 takes
Text-to-Image

The Halloween Invitation

While rendering simple text is no longer a real challenge for today’s SOTA models, this test shows something more interesting: how much visual taste a model has, and whether it can create a layout that feels like it came from a professional designer instead of a basic Canva template (no offense to Canva).

Prompt
“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.”
Judged on
  • Visual Taste
  • Text Accuracy
  • Layout
View full challenge
3
No entry yet
No entry yet
No entry yet
3
3
3
3
Text-to-Image

Magic Burger Explosion: Fiery Photorealism Challenge

3/8 · 9 takes
Text-to-Image

Magic Burger Explosion: Fiery Photorealism Challenge

This prompt forces models to simultaneously nail a highly specific, multi-layered commercial scene: dynamic exploded composition with multiple flying food elements, photorealistic textures, dramatic fiery lighting with embers, and precisely integrated glowing text, all while keeping strong visual impact. It is a perfect stress test that quickly separates models with true prompt mastery and creative control from those that miss details, break physics, or produce generic results.

Prompt
“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.”
Judged on
  • Fiery Atmosphere
  • Photorealism
  • Text integration
  • Visual Taste
View full challenge
3
No entry yet
3
No entry yet
No entry yet
No entry yet
No entry yet
3
Text-to-Image

Vintage Cafe Logo

3/8 · 9 takes
Text-to-Image

Vintage Cafe Logo

Prompt
“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.”
View full challenge
3
3
No entry yet
3
No entry yet
No entry yet
No entry yet
No entry yet
Text-to-Image

Isometric Miniature Diorama Scenes

3/8 · 9 takes
Text-to-Image

Isometric Miniature Diorama Scenes

Prompt
“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.”
View full challenge
3
3
No entry yet
3
No entry yet
No entry yet
No entry yet
No entry yet
Text-to-Image

Modern Clean Menu

3/8 · 9 takes
Text-to-Image

Modern Clean Menu

Prompt
“Modern minimalist restaurant menu design, white background with colorful food photos in grid, sections for appetizers/pizza/mains, bold sans-serif fonts, vibrant accents, clean professional layout for casual dining.”
Judged on
  • Readable text
  • 3 clear sections
  • visual taste
View full challenge
3
3
No entry yet
3
No entry yet
No entry yet
No entry yet
No entry yet
Text-to-Image

The Reversed Rodeo

2/8 · 6 takes
Text-to-Image

The Reversed Rodeo

This competition tests how well AI image models truly understand language versus how much they rely on visual habits from their training data. The prompt is deliberately simple on the surface but devilishly hard in practice. Most models default to the familiar trope of an astronaut riding a horse. By forcing the reversal, we measure three critical capabilities that separate good models from great ones:

  • Strict instruction following (including negations)
  • Accurate subject-object relationships and spatial hierarchy
  • Resistance to strong dataset biases
Prompt
“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Judged on
  • Horse actually on the back of the astronaut
View full challenge
No entry yet
No entry yet
No entry yet
No entry yet
3
No entry yet
3
No entry yet