GPT Image 1 Mini OpenAI Recraft V4 Recraft AI

Settled by community votes across 6 shared challenges, with an AI judge weighing in on each.

GPT Image 1 Mini

25.3 arena score

#12 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.

Recraft V4

26.4 arena score

#8 of 44 in Text-to-Image

Vote tally

Where the votes landed

GPT Image 1 Mini

0.0%

win rate

Ties

0.0%

Recraft V4

100.0%

win rate

0.0% 0.0% ties 100.0%

Shared challenges 6

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.”

GPT Image 1 Mini

Recraft V4

0% wins 0% ties 100% wins

AI Judge Analysis

GPT Image 1 Mini

+ Excellent adherence to lighting instructions with realistic soft diffusion
+ Clean and realistic glass refractions and transparency
+ Superior composition with a more natural placement of the background plant

− The glass cube looks more like a hollow glass box with very thin walls than a solid glass object

Recraft V4

+ Beautiful glass material with realistic thickness and caustic reflections
+ The sphere has a very sophisticated glass-on-glass look with complex lighting

− The blue sphere is floating unnaturally in the center of the cube
− The lighting on the cube and book feels slightly disconnected from the window in the background

Verdict: GPT Image 1 Mini followed the spatial instructions perfectly, placing the sphere on the bottom surface of the cube and correctly rendering the plant behind the glass. Recraft V4 produced a more visually striking glass effect, but the sphere is floating in mid-air, which breaks the physical logic of the scene.

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.”

GPT Image 1 Mini

Recraft V4

AI Judge Analysis

GPT Image 1 Mini

+ Excellent skin texture and aging detail on the face and hands
+ Accurate shallow depth of field with a 50mm feel
+ Realistic lighting and wet surfaces on the bicycle

− Anatomical issue with the hands merging into the bicycle frame
− Lacks the requested motion blur from passing cars
− Missing the visible 'light rain' atmosphere in the air

Recraft V4

+ Perfect adherence to the 'motion blur from passing cars' prompt
+ Strong composition that captures the 'candid street photo' atmosphere
+ Excellent reflections on the wet pavement and visible rain drops

− Bicycle structure is physically impossible with the front fork and frame intersection
− The subject's face is quite small and lacks the requested natural skin texture
− Some artifacts in the background elements and storefront signs

Verdict: Recraft V4 followed the complex environmental prompts much better, successfully incorporating motion blur, visible rain, and a candid street composition. However, GPT Image 1 Mini produced a far superior portrait with incredible skin detail and texture, though it failed the background motion and had significant clipping issues where the hands touched the bike. Overall, Recraft V4 is the winner for capturing the specific mood and technical requirements of the 'candid street' prompt despite the structural issues with the bicycle.

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.”

GPT Image 1 Mini

Recraft V4

0% wins 0% ties 100% wins

AI Judge Analysis

GPT Image 1 Mini

+ Excellent warm lighting and atmosphere with a strong cinematic feel.
+ Intricate engraving on the plate armor that looks very realistic.
+ High-quality skin texture and lifelike eyes.

− Missed the request for small beads in the braided hair.
− Leather straps and cloth underlayer are less prominent than in the other model.

Recraft V4

+ Strictly followed the request for beads in the braided hair.
+ Excellent rendering of the leather straps and buckle textures.
+ Good balance of battle damage, including clear dirt and scars.

− The lighting is a bit flatter and less atmospheric than the competitor.
− The armor design feels slightly more 'fantasy costume' than heavy plate.

Verdict: GPT Image 1 Mini creates a more visually stunning and atmospheric portrait with superior lighting and metal engraving, though it missed the specific detail of beads in the hair. Recraft V4 followed every technical prompt instruction including the beads and leather details, but the overall image feels slightly less cinematic. GPT Image 1 Mini is the likely winner for its superior visual quality and realism.

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.”

GPT Image 1 Mini

Recraft V4

0% wins 0% ties 100% wins

AI Judge Analysis

GPT Image 1 Mini

+ Excellent chalk-like texture on the lettering with realistic grainy edges
+ Perfect adherence to the full menu text prompt including the third item
+ Natural variations in letter size and spacing that mimic human handwriting

− Failed to provide the 'elegant cursive' style for the title as requested
− Composition is a tight crop rather than showing the 'cozy café' atmosphere

Recraft V4

+ Beautiful environmental composition showing the cozy café setting
+ Included creative chalk illustrations for each menu item
+ Very high overall visual quality and realistic lighting

− The text appears more like a digital font than natural chalk handwriting
− Missing the 'elegant cursive' requirement for the title
− Slightly less realistic chalk texture compared to the other model

Verdict: GPT Image 1 Mini followed the text instructions more accurately, providing the full menu list with superior chalk texture and handwriting characteristics. While Recraft V4 created a much more visually appealing and complete scene with the café background, its text rendering lacked the organic handwriting feel requested in 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.”

GPT Image 1 Mini

Recraft V4

AI Judge Analysis

GPT Image 1 Mini

+ Excellent fur texture and lighting on the capybara.
+ Successfully captures the bored, mundane expression of the passenger.
+ The lighting on the interior feels more consistent with a night scene.

− The steering wheel is poorly rendered and appears to clip into the driver's body.
− Only one paw is clearly visible on the steering wheel.

Recraft V4

+ Shows the full interior scene more clearly including the dash and door panels.
+ Accurately includes 'NYC Taxi' text on the cap and correctly positions both paws on the wheel.
+ Stronger sense of place with the visible rainy Manhattan skyline and World Trade Center in the background.

− The passenger's hair and face are a bit blurry and less detailed than the driver.
− The jacket color is more of a green-tone than the requested dark jacket.

Verdict: Recraft V4 is the winner as it offers a much better composition that shows the full interior context and accurately follows secondary instructions like the 'NYC Taxi' text and having both paws on the wheel. While GPT Image 1 Mini has impressive textures on the capybara, it fails on anatomy and physical objects like the mangled steering wheel.

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.”

GPT Image 1 Mini

Recraft V4

AI Judge Analysis

GPT Image 1 Mini

+ Excellent dynamic motion with all animals appearing to bounce and tumble.
+ Clean, uncluttered composition focusing clearly on the four subjects.
+ Beautiful warm lighting with soft, realistic fur textures.

− The fox's anatomy is slightly distorted, particularly the jaw and front leg.
− The god rays are a bit more generic compared to the intricate detail of the background in the other model.

Recraft V4

+ Exceptional detail in the environment, including dew sparkles and a wider variety of flora.
+ Anatomy of the fox and kitten is very accurate and well-rendered.
+ Stronger adherence to the '8K masterpiece' aesthetic with high-frequency details across the whole frame.

− The rabbit's pose looks slightly stiff or 'copy-pasted' into the center.
− The composition is a bit crowded with many butterflies, leading to a busier visual field.

Verdict: Both models followed the prompt exceptionally well, including all four requested animals. Recraft V4 wins slightly due to its superior rendering of fine details like dew sparkles and more accurate animal anatomy, whereas GPT Image 1 Mini has slightly better sense of playful movement but suffers from a few minor anatomical artifacts on the fox.