OpenAI's legacy image generation model supporting generations, edits with masks (inpainting), and variations
Settled by community votes across 13 shared challenges, with an AI judge weighing in on each.
DALL-E 2
17.7
arena score
#37 of 44 in Text-to-Image
Skill signature
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
Nano Banana 2
29.0
arena score
#1 of 44 in Text-to-Image
Best Text-to-Image right now
Top 2 in Image Editing
Vote tally
Where the votes landed
DALL-E 2
0.0%
win rate
Ties
0.0%
Nano Banana 2
100.0%
win rate
0.0%
0.0% ties
100.0%
Shared challenges
13
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Features a wooden table with accurate reflections
- − Failed to include a blue sphere
- − Failed to place a red book on top of the cube
- − Large blue object in background is not a green plant
- − Cube contains a red rectangular shape instead of being empty with a sphere
Nano Banana 2
- + Perfect adherence to all prompt elements including sphere, cube, book, and plant
- + Excellent visual quality and logical spatial arrangement
- + Realistic lighting and appropriate plant visibility through glass
- − The book is slightly floating on the right side over the glass edge
Verdict: Nano Banana 2 followed every instruction in the prompt, successfully placing a red book on top of a glass cube that contains a blue sphere, with a plant visible behind it. DALL-E 2 failed significantly, missing almost all spatial instructions and objects, resulting in a composition that bore little resemblance to the request. Nano Banana 2 is the clear winner for its high level of detail and conceptual accuracy.
Candid Street Photography
Text-to-Image“A candid street photo of an elderly Japanese man repairing a red bicycle in light rain, reflections on wet pavement, shallow depth of field, 50mm lens, natural skin texture, imperfect framing, motion blur from passing cars, cinematic but realistic, no stylization.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Good use of foreground blurring for an imperfect, candid feel.
- + Captured realistic wet pavement reflections.
- − The subject is completely out of focus and unrecognizable.
- − Fails to show an 'elderly Japanese man' or 'repairing' effectively due to extreme blur.
- − Missing the motion blur from cars requested.
Nano Banana 2
- + Perfect adherence to all prompt elements including context, character, and action.
- + Excellent rendering of textures on the face, clothing, and wet street.
- + Authentic Japanese street setting with legible shop signage and realistic lighting.
- − The motion blur on the car in the background is a bit subtle.
- − The bicycle chain geometry is slightly physically impossible where it connects to the wrench.
Verdict: Nano Banana 2 delivered a highly detailed, cinematic, and accurate representation of the prompt, capturing the specific cultural setting and the elderly man's features perfectly. DALL-E 2 produced an abstract, heavily blurred image that failed to show the requested subject or action clearly, making it unusable for the specific request.
Fantasy Warrior
Text-to-Image“Close portrait of a battle-worn paladin in ornate engraved plate armor, hair braided with small beads, faint scars and dirt on the skin, warm torchlight reflecting off metal, shallow depth of field, bokeh sparks, lifelike eyes, highly detailed texture on leather straps and cloth underlayer.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Successfully captures a tight macro perspective
- + Good use of bokeh
- − Extremely poor visual quality with severe noise and compression artifacts
- − Failed to render a recognizable face or the specific details requested like braids and lifelike eyes
- − Anatomy is incoherent and messy
Nano Banana 2
- + Excellent adherence to all prompt details including braids with beads, scars, and ornate armor
- + High visual fidelity with impressive skin and metal textures
- + Masterful lighting and composition
- − Minor distortion on the sword hilt where the hand grips it
Verdict: Nano Banana 2 delivered a high-quality, professional image that followed every detail of the prompt, including the complex request for braided hair with beads and lifelike eyes. DALL-E 2 produced a low-resolution, noisy output that failed to accurately represent a human face or the required textures.
Modern Clean Menu
Text-to-Image“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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Bold, expressive typography that fits a minimalist aesthetic
- + Interesting abstract use of food photography as geometric elements
- − Nonsensical text that fails to represent a functional menu
- − Poor rendering of food items with heavy digital artifacts
- − Fails to include the specific categories (Appetizers/Pizza/Mains) requested
Nano Banana 2
- + Excellent adherence to all prompt instructions including specific food categories
- + Highly legible and professional use of sans-serif typography
- + High-quality, realistic food photography in a clean grid layout
- − Minor spelling errors in smaller body text
- − The layout is slightly more traditional than purely minimalist
Verdict: Nano Banana 2 is the clear winner as it produced a fully functional and professional restaurant menu design that strictly followed the prompt's layout and content requirements. DALL-E 2 produced an abstract, distorted image with garbled text that failed to meet the basic criteria of a professional menu design.
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Captures a strong sense of fiery motion and energy
- − Text is nonsensical and does not follow the prompt
- − Burger components are messy, poorly defined, and lack photorealism
- − Missing the starburst and specific price information
Nano Banana 2
- + Excellent text rendering, accurately following all specific prompt requirements
- + High photorealistic detail on all food components including sauce splashes
- + Well-balanced commercial composition with a clear starburst element
- − The burger components are neatly stacked rather than wildly 'exploded' vertically
Verdict: Nano Banana 2 followed every instruction in the prompt, including complex text rendering of names, prices, and secondary messages. DALL-E 2 failed significantly on the text, producing gibberish, and the visual quality of the food was much lower and harder to distinguish.
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + The chalk texture on the individual letters feels thick and realistic.
- − The text is completely illegible gibberish.
- − The prompt's specific menu items and date are entirely ignored.
- − The composition is a tight, low-resolution crop with no cafe background.
Nano Banana 2
- + Excellent prompt adherence with near-perfect spelling of all requested items.
- + The composition includes a realistic, high-quality cafe background with depth of field.
- + The text rendering successfully simulates the variations of a chalk medium.
- − The 'Brown Butter' item is completed despite the prompt cutting off, which is a logic leap.
- − The handwriting looks slightly more like a digital font than natural handwriting in a few places.
Verdict: Nano Banana 2 followed the prompt almost perfectly, correctly rendering the complex menu items and date with high legibility and a pleasant cafe aesthetic. DALL-E 2 failed to produce legible text or follow the specific content instructions, resulting in a disorganized mess of symbols. Nano Banana 2 is the clear winner for both its technical execution and adherence to detail.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Successfully captures a surreal, lonely atmosphere.
- + Adheres to the color palette typically associated with space imagery.
- − Fails the prompt's core spatial requirement by placing the astronaut on top of the horse.
- − Low resolution and lacks 'highly detailed' cinematic qualities requested.
- − Visible warping and anatomy issues on the horse's legs.
Nano Banana 2
- + Perfectly follows the specific instruction of having the horse on top of the astronaut.
- + High visual quality with vibrant colors and sharp details.
- + Dynamic composition that creates a sense of movement in space.
- − The horse's harness is physically impossible and floating strangely.
- − The tethering between the horse and astronaut is visually cluttered.
Verdict: Nano Banana 2 followed the complex spatial instructions perfectly, depicting a horse on top of an astronaut, whereas DALL-E 2 produced a standard 'astronaut on a horse' image. Nano Banana 2 also provided significantly higher resolution and cinematic detail compared to the grainy output of DALL-E 2.
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- − The image is a complete failure, showing a close-up of a black leather bag instead of the requested scene.
- − Does not follow any part of the prompt.
Nano Banana 2
- + Excellent adherence to all prompt details including the capybara's outfit, pose, and the New York setting.
- + High visual quality with detailed textures on the fur and realistic interior lighting.
- + Strong composition that captures the surreal nature of the driver while maintaining a realistic atmosphere.
- − The businesswoman in the back seat is missing/not visible in this specific framing.
- − Minor anatomical oddity on the paws gripping the wheel.
Verdict: DALL-E 2 suffered a total failure, producing an image of a black handbag that bore no relation to the prompt. Nano Banana 2 provided a high-quality, atmospheric, and creative interpretation of a capybara taxi driver in Manhattan, following almost every instruction perfectly.
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Captures a vintage hand-painted feel
- + Includes basic elements like bat silhouettes and trees
- − Text is illegible and mostly gibberish
- − Fails to include several specific details like the jack-o-lantern and custom event info
- − Low resolution with significant artifacts
Nano Banana 2
- + Excellent text rendering with accurate spelling and elegant gothic fonts
- + High-quality, cinematic illustration style with great lighting
- + Follows all prompt instructions including specific date, time, and location
- − None notable
Verdict: Nano Banana 2 is the clear winner as it perfectly executes the graphic design task, rendering all requested text accurately and placing it within a beautiful, high-quality illustration. DALL-E 2 fails to produce legible text and lacks the requested central jack-o-lantern and specific event details.
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Clean isometric perspective
- + Good 3D lighting and shadow work
- − Incomplete and misspelled text ('Sush' instead of 'SUSHI')
- − Missing 'JAPAN' text and flag icon
- − Very poor aesthetic quality with distorted models that do not resemble appetizing sushi
Nano Banana 2
- + Perfect adherence to text layout and spelling requirements
- + Excellent realistic PBR materials and textures
- + Highly detailed and appetizing 'miniature' diorama aesthetic with a consistent isometric perspective
- − The garnish exceeds the 'minimal' request slightly
Verdict: Nano Banana 2 followed every instruction in the prompt, including the specific text placement, the flag, and the 3D isometric style. In contrast, DALL-E 2 failed on almost all semantic and aesthetic levels, providing misspelled text and unidentifiable shapes.
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.”
DALL-E 2
Nano Banana 2
0% wins
0% ties
100% wins
AI Judge Analysis
DALL-E 2
- + Captures the golden sunrise light and a sense of dynamic movement.
- − Significant anatomical local distortions and 'melting' on the animals.
- − Low resolution with visible compression artifacts.
- − Missing the bunny and poorly defined fox/kitten.
Nano Banana 2
- + Successfully includes all four requested animals with distinct features.
- + Excellent rendering of 'god rays', dew sparkles, and detailed fur texture.
- + High-quality composition with coherent anatomy and vibrant wildflowers.
- − The lighting on the animals is slightly too uniform compared to the strong backlighting of the sun.
- − The butterflies are somewhat static in their placement.
Verdict: Nano Banana 2 is the clear winner as it successfully rendered all four requested animals (puppy, kitten, bunny, and fox kit) with high detail and anatomical correctness. DALL-E 2 struggled significantly with the prompt, producing heavily distorted figures and failing to include the bunny entirely.
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Successfully uses a warm brown and cream color palette.
- + Includes a minimalist cloche icon.
- − The text is completely unintelligible and fails to spell 'Caffè Florian'.
- − Missing the required banner and date.
- − Graphics are shaky and lack the clean vector finish requested.
Nano Banana 2
- + Perfect text rendering for both 'Caffè Florian' and 'Est. 1720'.
- + Excellent composition with a professional emblem style and banner.
- + Includes all prompt elements including steam and subtle background texture.
- − Slightly more detailed than 'minimalist' might imply, leaning more towards 'vintage ornate'.
Verdict: Nano Banana 2 is the clear winner as it perfectly adheres to every part of the prompt, including complex text and specific layout elements like the banner. DALL-E 2 fails significantly on the typography, producing nonsensical characters and missing the established date entirely.
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.”
DALL-E 2
Nano Banana 2
AI Judge Analysis
DALL-E 2
- + Features a tech-focused color palette consistent with the prompt.
- − Text is nonsensical and includes major spelling errors like 'ALLPOO'.
- − The layout is chaotic and fails to follow the requested 6-step chronological structure.
- − Icons are abstract and unrecognizable as NASA/Apollo elements.
Nano Banana 2
- + Perfectly follows the 6-step sequence with accurate iconography for each phase.
- + Text is highly legible and correctly spelled, including astronaut names and mission phases.
- + Maintains a clean, professional flat-vector aesthetic with the requested color palette.
- − Includes a fourth anonymous astronaut silhouette when the mission only had three.
Verdict: Nano Banana 2 followed the prompt instructions near-perfectly, creating a structured, educational infographic with clear icons and accurate text. In contrast, DALL-E 2 produced a cluttered, incomprehensible image with significant 'spelling' issues and a lack of clear narrative flow. Nano Banana 2 is much more useful for an actual poster design.
Next steps
Explore each model
Gemini 3.1 Flash with image generation capabilities. High-efficiency image generation model with support for text rendering, reference images, search grounding, and thinking mode. The efficient counterpart to Gemini 3 Pro Image.