Head to head
Esc

Models · slot A

to navigate to pick

FLUX.1 Kontext [dev] Black Forest Labs Wan 2.7 Pro Alibaba

Settled by community votes across 17 shared challenges, with an AI judge weighing in on each.

FLUX.1 Kontext [dev]

17.1 arena score

#54 of 62 in Text-to-Image

Skill signature · Text-to-Image

Wan 2.7 Pro

21.0 arena score

#37 of 62 in Text-to-Image

Vote tally

Where the votes landed

FLUX.1 Kontext [dev]

0.0%

win rate

Ties

0.0%

Wan 2.7 Pro

100.0%

win rate

0.0% 0.0% ties 100.0%
Shared challenges 17

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent adherence to the 'partial visibility' through the glass cube
  • + Vibrant, clean colors and sharp contrast
  • + High-quality rendering of light reflections on the sphere
  • The glass cube lacks a bottom face or clear edges at the base
  • The sphere appears floating or improperly grounded

Wan 2.7 Pro

  • + Realistic wooden table texture and weathered details
  • + The blue sphere has a more natural, marble-like texture
  • + Better sense of scale and spatial depth
  • The plant is seen through the glass but less clearly than in Model A
  • The cube edges are slightly inconsistent near the book base

Verdict: Both models followed the spatial requirements of the prompt perfectly. FLUX.1 Kontext [dev] produced a cleaner, more commercial-style image with vibrant colors, while Wan 2.7 Pro offered a more photorealistic, rustic aesthetic with superior texture work on the wood and sphere. FLUX.1 Kontext [dev] is slightly preferred for its more explicit rendering of the plant visible through the glass.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent handling of wet pavement reflections
  • + Follows the shallow depth of field requirement well
  • The man appears to be sitting on or walking with the bike rather than actively repairing it
  • Missing the requested motion blur from passing cars
  • The rain effect looks like a simple digital overlay

Wan 2.7 Pro

  • + Successfully depicts the 'repairing' action with focused attention on the handlebars
  • + Achieves a more 'candid' and realistic street photography aesthetic
  • + The bicycle design and wear feel more authentic to a used red bike
  • The background cars are static rather than having the requested motion blur
  • The 'imperfect framing' is subtle, though arguably present in the cropping of the background van

Verdict: Wan 2.7 Pro is the clear winner as it captures the 'repairing' action requested in the prompt, whereas FLUX.1 Kontext [dev] shows a man simply standing with a bicycle. Wan 2.7 Pro also leans more into the gritty, realistic street photography style requested, while FLUX.1 Kontext [dev] feels slightly more staged and clean.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent dramatic lighting and high-contrast composition
  • + Highly intricate engraving patterns on the breastplate
  • + Clean and cinematic bokeh effect
  • Failed to include the requested braided hair with beads
  • Skin appears too smooth and lacks the 'faint scars and dirt' requested
  • The armor lacks a realistic metallic texture, appearing somewhat like plastic or resin

Wan 2.7 Pro

  • + Perfect adherence to specific details like braided hair with beads and facial scars
  • + Realistic metallic texture with visible dirt, wear, and torchlight reflections
  • + Exceptional detail on leather straps and fabric underlayers
  • The bokeh sparks appear a bit more artificial compared to the ambient lighting
  • Background torches are slightly distracting compared to the more focused composition in Model A

Verdict: Wan 2.7 Pro is the clear winner as it followed every instruction in the prompt, including the specific hair style, beads, and realistic battle-worn skin textures. FLUX.1 Kontext [dev] produced a high-quality cinematic image, but it failed to render several key descriptive elements like the braids and the weathered appearance of the character.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + High-quality, vibrant food photography
  • + Clean minimalist layout with successful use of white space
  • Nonsensical text and broken lettering
  • Layout is abstract and lacks a functional menu flow
  • No clear sections for pizza or mains as requested

Wan 2.7 Pro

  • + Excellent adherence to all prompt elements including specific sections
  • + Clear, legible typography and logical menu structure
  • + Cohesive visual identity with logo, QR code, and pricing
  • Some minor spelling errors in item descriptions
  • Food images are slightly small and less detailed compared to Model A

Verdict: Wan 2.7 Pro is the clear winner for this task as it produced a fully functional, professional restaurant menu that strictly followed all prompt instructions including category sections. While FLUX.1 Kontext [dev] produced higher-quality individual food photos, it failed to create a usable menu structure and the text was entirely garbled.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro
0% wins 0% ties 100% wins

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Clean and readable primary typography.
  • + Strong color contrast with vibrant orange and dark coals.
  • + High level of photorealism in the patty texture.
  • Fails the 'exploded' motion requirement, showing a mostly assembled burger.
  • Contains a spelling error in the secondary text ('LNHLY').

Wan 2.7 Pro

  • + Perfectly executes the 'exploded' burger concept with dynamic movement.
  • + Correctly renders all requested text without spelling errors.
  • + Effectively integrates fiery glowing effects on the lettering and background.
  • Slightly busy composition with many small floating herb particles.
  • The glowing effect on the bottom starburst is less intense than the top text.

Verdict: Wan 2.7 Pro is the clear winner as it successfully followed the complex instruction for an 'exploded' burger view and rendered all text accurately. FLUX.1 Kontext [dev] failed to separate the burger components and included a typographical error in the secondary message.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Features a bold, thick chalk texture
  • + Accurately represents a plain wooden frame on a wall
  • Numerous spelling errors including 'Mashroom', 'Risoktso', and 'Octpus'
  • Repetitive words ('with with') and garbled date text
  • Messy layout with overlapping prices and inconsistent font sizes

Wan 2.7 Pro

  • + Excellent spelling accuracy for the entire requested text
  • + Consistently elegant and legible handwriting style as requested
  • + Highly realistic chalkboard texture including smudges and dust
  • + Better overall composition and cozy café background
  • The 'cursive' request for the title is interpreted more as a stylized print than true cursive script

Verdict: Wan 2.7 Pro is the clear winner as it followed the complex text requirements perfectly without a single spelling error, whereas FLUX.1 Kontext [dev] struggled with basic spelling and layout, resulting in a cluttered and illegible board. Wan 2.7 Pro also provided a much more atmospheric and aesthetically pleasing background that fit the 'cozy café' prompt.

The Reversed Rodeo

Text-to-Image

“Horse riding astronaut in space — horse on top, not vice versa. Surreal, highly detailed, cinematic.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Successfully followed the difficult logic of the horse being on top of the astronaut
  • + High facial detail and realistic textures on the spacesuit
  • + Cinematic lighting with a clear sense of depth and focus
  • The horse's placement is somewhat clipping into the astronaut rather than being a distinct rider
  • The background space elements look like simple grey spheres

Wan 2.7 Pro

  • + Excellent background composition with detailed planets and atmosphere
  • + Anatomically correct horse and detailed harness/saddle
  • + Very high resolution and clarity
  • Completely failed the negative constraint/logic change (astronaut is riding the horse)
  • Traditional rather than surreal interpretation

Verdict: FLUX.1 Kontext [dev] is the clear winner because it successfully interpreted the specific and unusual instruction to place the horse on top of the astronaut. Wan 2.7 Pro produced a high-quality image, but it defaulted to a standard trope and ignored the core request of the prompt.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent photorealism and cinematic lighting.
  • + High-quality fur texture and realistic facial features on both subjects.
  • + Successfully captures the bored, mundane expression of the businesswoman.
  • The capybara only has one paw on the steering wheel while the other rests on its lap.
  • The woman is sitting directly behind the driver instead of more naturally to the side for the camera angle.

Wan 2.7 Pro

  • + Perfectly depicts both front paws on the steering wheel as requested.
  • + The yellow taxi driver cap is more stylish and fits the character well.
  • + Good composition with the street view visible through the side window.
  • Major spatial error with the businesswoman sitting in the front passenger seat instead of the back seat.
  • The hands/paws of the capybara look more like primate hands than capybara paws.
  • The taxi interior feels cramped and slightly distorted.

Verdict: FLUX.1 Kontext [dev] produced a far superior image in terms of lighting, texture, and realism, despite missing the minor instruction for 'both' paws on the wheel. Wan 2.7 Pro followed the physical movement instructions better but failed on the key compositional element of the passenger being in the back seat, and the rendering of the paws was anatomically uncanny.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Strong, high-contrast lighting on the jack-o-lantern
  • + Clean main title text rendering
  • Substantial spelling errors in the scroll banner and location text
  • Missing 'parchment' texture, featuring a plain black background instead

Wan 2.7 Pro

  • + Perfect text rendering for all requested details, including date and location
  • + Highly detailed composition with thorns, webs, and a parchment-style border
  • + Excellent thematic adherence to the 'vintage gothic' and 'moody sky' prompts
  • Slightly more illustrated/cartoonish style compared to a 'cinematic' look

Verdict: Wan 2.7 Pro is the clear winner as it followed every instruction in the prompt, including complex text rendering for the date and location, whereas FLUX.1 Kontext [dev] failed significantly on text accuracy and background texture. Wan 2.7 Pro also successfully integrated all visual elements like the webs, thorns, and parchment, creating a much more complete and professional-looking invitation.

Bald man challenge

Image Editing
Edit instruction

“Give the person a full, thick head of natural hair with realistic texture, density, and a natural hairline. Preserve facial features and lighting.”

Before After
FLUX.1 Kontext [dev]
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Provides a very thick and full head of hair as requested.
  • + Maintains the general composition and clothing of the source image.
  • Significantly alters the facial structure, making the man look younger and thinner.
  • The hair texture looks somewhat artificial and 'painted on' at the hairline.
  • Changes the frame and color of the eyeglasses.

Wan 2.7 Pro

  • + Excellent preservation of the original facial features and bone structure.
  • + The hair texture is extremely realistic and looks naturally integrated with the existing beard.
  • + Maintains the exact glasses and lighting from the source image.
  • The hair is slightly less 'full' than Model A, but still meets the prompt requirements.

Verdict: Wan 2.7 Pro is the clear winner as it successfully adds a natural head of hair while perfectly preserving the identity of the person in the source image. FLUX.1 Kontext [dev] fails the source preservation requirement by significantly changing the man's facial features and glasses, making him look like a different person.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent text rendering and alignment
  • + Very clean, minimal aesthetic
  • + Accurate 45 degree isometric perspective
  • Flag icon is an abstract geometric shape rather than a Japanese flag
  • The sushi model is overly simplified, bordering on toy-like rather than refined miniature

Wan 2.7 Pro

  • + Superior PBR materials and textures for food
  • + Detailed variety of sushi models
  • + Accurate national flag icon
  • Included extra text and random scatter elements not in prompt
  • The isometric angle is slightly flatter than the requested 45 degrees
  • Diagonal layout makes the 'perfectly centered' requirement feel less balanced

Verdict: FLUX.1 Kontext [dev] followed the layout and centering instructions perfectly with very bold, clean text, but the central subject was too simplistic. Wan 2.7 Pro created much more appealing textures and realistic miniature food, though it added extraneous elements and text that strayed from the 'ultra-clean' requirement. Overall, Wan 2.7 Pro is the winner because the visual quality of the 3D sushi is significantly better.

Over-the-top cartoon caricature

Editing
Edit instruction

“Create a caricature of me and my job. Make it exaggerated and humorous, incorporating my profession as a tv show anchor and my love for dogs and hockey.”

Source
FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Maintains the subject's clothing and pose from the source image
  • + Successfully interprets the requested caricature style with vibrant colors
  • + Incorporate the TV anchor and dog elements into the scene background
  • Completely misses the 'hockey' requirement
  • The text elements ('JOB') feel generic and unrelated to the prompt

Wan 2.7 Pro

  • + Excellent adherence to all prompt elements including TV anchor suit, multiple dogs, and a hockey stick microphone hybrid
  • + High level of exaggeration appropriate for a caricature
  • + Strong text rendering for the speech bubbles
  • Loses the original clothing and specific selfie-style pose from the source image
  • The hand holding the hockey stick has anatomical errors (merged fingers)

Verdict: Wan 2.7 Pro is the clear winner for its comprehensive adherence to the prompt, successfully blending all requested elements (TV anchor, dogs, and hockey) into a cohesive and humorous caricature. While FLUX.1 Kontext [dev] preserved the original pose and denim shirt better, it completely ignored the hockey instruction and felt less creative in its interpretation of the requested profession.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent depiction of motion and energy
  • + Beautiful highlights and consistent warm lighting
  • + Clean, toy-like adorable aesthetic
  • Failed to include the baby bunny and red fox kit
  • Included two kittens instead of the requested species variety
  • Anatomical issues with the front paws on the far-right kitten

Wan 2.7 Pro

  • + Perfect adherence to the complex list of animals (dog, cat, rabbit, fox)
  • + Stunning lighting with visible god rays and dew sparkles as requested
  • + Incredible texture detail in the fur and surrounding wildflowers
  • The fox kit's back leg/tail area is slightly messy in the grass
  • The puppy's left ear has a slightly unnatural transition into the head

Verdict: Wan 2.7 Pro is the clear winner as it successfully rendered all four distinct animal species mentioned in the prompt, whereas FLUX.1 Kontext [dev] only generated a puppy and two kittens. Wan 2.7 Pro also captured the specific lighting details like god rays and dew sparkles with much higher fidelity and variety in the meadow flora.

Studio Ghibli Anime Style

Editing
Edit instruction

“Transform this photo into a Studio Ghibli–inspired illustration. Use soft pastel colors, hand-painted textures, gentle lighting, dreamy backgrounds, and a warm, nostalgic mood”

Source
FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent preservation of the original pose and character layout
  • + Clean, digital anime aesthetic with clear linework
  • + Accurately replicates the expressions from the original meme in a new style
  • Lean too much toward modern generic anime rather than the specific 'hand-painted' Ghibli look
  • Colors feel saturated rather than the requested soft pastels

Wan 2.7 Pro

  • + Perfectly captures the hand-painted, watercolor texture requested
  • + Excellent use of soft pastel colors and gentle lighting
  • + Preserves the likeness and facial anatomy of the original subjects more accurately than Model A
  • The watercolor bleed on the edges of the woman in the red dress is slightly messy in some spots

Verdict: Wan 2.7 Pro is the clear winner as it successfully interpreted the 'Studio Ghibli' and 'hand-painted' prompts by applying a beautiful watercolor texture and pastel palette. FLUX.1 Kontext [dev] produced a high-quality image but defaulted to a standard flat digital anime style, failing to capture the textural nuances requested.

Golden Hour Stroll

Image Editing
Edit instruction

“Add dynamic motion to this photo: make hair blow in the wind, add leaves flying, energetic and lively feel.”

Before After
FLUX.1 Kontext [dev]
Before After
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent source preservation of the woman's face and original features
  • + Subtle and natural-looking wind effect on the hair
  • The 'flying leaves' are very sparse, appearing as just a few small green specks
  • Lacks the 'energetic and lively' feel requested in the prompt

Wan 2.7 Pro

  • + Highly dynamic and energetic hair movement that significantly transforms the mood
  • + Numerous flying leaves successfully create a sense of motion throughout the frame
  • Noticeable facial distortion on the subject compared to the original image
  • Some leaves appear slightly blurred or mismatched in lighting with the scenery

Verdict: Wan 2.7 Pro followed the motion instructions much more effectively, creating a truly energetic scene with wind-blown hair and numerous flying leaves. While FLUX.1 Kontext [dev] preserved the subject's face better, it failed to provide the requested level of dynamic motion, offering only a very subtle hair adjustment and almost no visible leaves.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Excellent typography with perfect spelling of 'Caffè Florian'
  • + Clean, minimalist vector aesthetic that fits the modern logo style
  • + Highly legible and well-balanced composition
  • Missed the 'banner' requirement for the Est. 1720 text
  • The cloche illustration is very abstract, bordering on looking like a building dome

Wan 2.7 Pro

  • + Successfully included the requested banner and steam elements
  • + Sophisticated vintage aesthetic with good use of texture
  • + Accurate representation of a cloche dome
  • Spelling error in the primary brand name ('Florion' instead of 'Florian')
  • Cluttered composition with floating corner elements that detract from the logo
  • Text spacing is slightly uneven in the main title

Verdict: While Wan 2.7 Pro captured more of the stylistic prompts like the banner and detailed cloche, its failure to spell the name 'Caffè Florian' correctly is a significant drawback for a logo. FLUX.1 Kontext [dev] followed the core minimalism and typography requirements with perfect spelling, making it the more professional and usable asset despite missing the banner detail.

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.”

FLUX.1 Kontext [dev]
Wan 2.7 Pro

AI Judge Analysis

FLUX.1 Kontext [dev]

  • + Strongly adheres to the requested color palette
  • + Good vector-style flat aesthetic
  • Severely garbled text and typos (e.g., 'APOLO')
  • Layout is cluttered and lacks logical flow
  • Iconography is abstract and difficult to recognize

Wan 2.7 Pro

  • + Highly legible and mostly accurate text
  • + Excellent linear composition that follows the mission steps
  • + Clean, consistent iconography that matches the prompt's specific icons
  • Minor typo in 'DESCRIPT' (should be Descent)
  • Small visual artifact in the star field distribution

Verdict: Wan 2.7 Pro followed the instructions much more effectively, producing a coherent, professional-grade infographic with a logical flow of information. FLUX.1 Kontext [dev] struggled with basic text rendering, including misspelling the main title, and failed to create a readable layout.

Next steps

Explore each model