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.
Settled by community votes across 5 shared challenges, with an AI judge weighing in on each.
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
Skill signature
Not enough comparable category data
The chart appears once both models have ratings across at least three shared arena categories.
Wan 2.7
19.0
arena score
#34 of 44 in Text-to-Image
Vote tally
Where the votes landed
Nano Banana 2
0%
win rate
Ties
0%
Wan 2.7
0%
win rate
Shared challenges
5
Challenge by challenge
The strongest take from each model on every shared challenge, with the AI judge's read.
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.”
Nano Banana 2
Wan 2.7
AI Judge Analysis
Nano Banana 2
- + Excellent text accuracy including the inferred completion of the truncated prompt.
- + High-quality realistic chalk texture with smudges and varying opacity.
- + Convincing handwritten style that matches the cozy cafe setting.
- − The layout is a bit slightly centered with large gaps between lines.
Wan 2.7
- + Perfect text rendering for all requested items.
- + Excellent layout and composition with decorative dividers.
- + Consistent font style throughout the board.
- − The text looks more like a digital font or 'sticker' overlays rather than real chalk on a board.
- − Shadows behind the letters make it look less like natural handwriting.
Verdict: Nano Banana 2 is the clear winner as it perfectly captures the requested 'chalk texture' and 'handwritten style', looking significantly more like a real chalkboard. While Wan 2.7 has excellent text accuracy and layout, the letters appear like a clean digital font applied over a background, failing the prompt's request for natural chalk variations.
The Reversed Rodeo
Text-to-Image“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”
Nano Banana 2
Wan 2.7
AI Judge Analysis
Nano Banana 2
- + Successfully followed the difficult spatial instruction of having the horse on top.
- + Highly detailed rendering of both the spacesuit and the horse's musculature.
- + Vibrant, cinematic colors and a strong sense of surrealism.
- − The connection between the horse's hoof and the astronaut's helmet is a bit awkward.
- − The reins are floating somewhat unnaturally in the middle of the frame.
Wan 2.7
- + Clean, clear composition with a nice contrast against the planetary curve.
- + High quality rendering of the astronaut's suit and the horse's coat.
- − Failed the primary logic constraint by placing the astronaut on top of the horse.
- − The horse's legs show some anatomical merging with the horizon line.
Verdict: Nano Banana 2 was the only model to follow the specific surreal instruction to have the horse on top of the astronaut. Wan 2.7 produced a high-quality but generic image that ignored the core 'not vice versa' prompt requirement.
Outfit Transfer Challenge
EditingEdit instruction
“Use Image 1 as the base person. Dress them in the exact elaborate outfit from Image 2 (including all layers, accessories, jewelry, and shoes). Carefully adapt the clothing to the body shape and pose in Image 1 while maintaining realistic fabric behavior, correct proportions, and perfect lighting/shadow matching. Keep the person’s exact face, hair, and background completely unchanged.”
Source
Nano Banana 2
Wan 2.7
AI Judge Analysis
Nano Banana 2
- + Perfectly replicates the specific clothing items from Image 2, including the exact scarf and coat.
- + Maintains high-quality skin texture and preserves the specific vitiligo patterns on the subject's face.
- + Accurately integrates the sunglasses and ring from the reference image.
Wan 2.7
- + Good full-body composition and lighting integration with the beach environment.
- + Creative interpretation of an 'elaborate' outfit that fits the subject well.
- + Correctly adapts the pose to the new clothing.
- − Completely ignored the clothing in Image 2, generating a generic gold-trimmed coat instead.
- − Changed the character's facial features and expression, losing the likeness of the original subject.
- − The clothing style is inconsistent with the requested source material.
Verdict: Nano Banana 2 followed the strict editing instructions perfectly, accurately transferring the exact coat, scarf, and accessories from Image 2 onto the subject while preserving their facial identity and the background. Wan 2.7 failed the primary task of using the specific clothing provided in the source image, instead generating a completely different outfit and altering the person's face.
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.”
Nano Banana 2
Wan 2.7
AI Judge Analysis
Nano Banana 2
- + Excellent photorealistic texture on the capybara's fur and clothing.
- + Atmospheric lighting with high-quality interior taxi details like the fare meter and GPS.
- + Superior depiction of the New York night scene through the windshield.
- − Fails to show the human businesswoman in the back seat.
- − The capybara's paws are rendered a bit more like human hands.
Wan 2.7
- + Successfully includes both the capybara driver and the bored businesswoman in the scene.
- + Good adherence to the 'both paws on the steering wheel' instruction.
- + Clearer view of the yellow taxi exterior which was implied in the prompt.
- − The capybara's fur looks slightly less realistic and more like a mask or illustration.
- − The businesswoman is sitting in the front passenger seat instead of the requested back seat.
Verdict: Nano Banana 2 produces a much more cinematic and high-fidelity image with stunning lighting and textures, but it completely misses the requirement for a passenger. Wan 2.7 follows the prompt much better by including the businesswoman, though both models struggled with her exact spatial placement (she is in the front seat instead of the back). Nano Banana 2 is visually superior, but Wan 2.7 is the better functional interpretation of the request.
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.”
Nano Banana 2
Wan 2.7
AI Judge Analysis
Nano Banana 2
- + Excellent typography with a cohesive gothic style.
- + Perfect adherence to all specific text requirements including date and location.
- + Cinematic lighting with a higher level of atmospheric detail in the background.
- − The parchment edges are slightly clipped in the square format crop.
Wan 2.7
- + Clean layout with a distinct illustrated border incorporating thorns and webs.
- + Includes extra creative elements like a cauldron and books that fit the theme.
- + Great legibility on the smaller scroll banner.
- − Missed the 'elegant gothic title' instruction, using a more standard serif font for the main header.
- − The art style is slightly more 'cartoony' compared to the requested 'cinematic' gothic look.
Verdict: Nano Banana 2 followed the prompt's aesthetic and typographic instructions much more closely, delivering a cohesive 'cinematic gothic' poster with impressive text rendering. While Wan 2.7 produced a clean and legible invitation, its font choices were less gothic and the overall mood was brighter and more illustrated than the dark, moody atmosphere requested.
Next steps
Explore each model
Alibaba's Wan 2.7 image generation and editing model for text-to-image, reference-guided generation, and instruction-based image edits