GPT Image 1 Mini vs GPT Image 1.5
Head-to-head across 4 challenges
GPT Image 1 Mini
25.0%
win rate
Ties
0.0%
GPT Image 1.5
75.0%
win rate
Challenge Results
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.”
AI Judge Analysis
GPT Image 1 Mini
- + Excellent photorealism and textures, especially on the book's paper and cover.
- + Creates a very clean, aesthetically pleasing composition with soft, cinematic lighting.
- − The plant is placed to the side rather than behind the cube as requested.
- − The sphere appears to be floating inside the cube, which feels less physically grounded.
GPT Image 1.5
- + Strictly follows the spatial instruction of placing the plant behind the cube.
- + Handles complex glass reflections and refractions accurately, including the reflection of the sphere on the bottom pane.
- + Better adherence to the 'small blue sphere' prompt as the sphere is more in proportion to the cube.
- − The lighting is a bit harsher and less 'soft' than requested.
- − The textures on the desk and book are slightly less refined compared to the competitor.
Verdict: GPT Image 1.5 is the winner because it successfully followed the difficult spatial instruction of placing the plant behind the cube, allowing it to be seen through the glass. While GPT Image 1 Mini produced a more visually artistic image with superior textures, it failed the core relational prompt regarding the plant's position.
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.”
AI Judge Analysis
GPT Image 1 Mini
- + Excellent shallow depth of field creates a cinematic look.
- + Beautiful reflections on the wet pavement.
- + Natural skin texture and realistic expression on the subject.
- − The structural anatomy of the bicycle is slightly nonsensical with overlapping frames and spokes.
- − Lacks the requested motion blur from passing cars.
GPT Image 1.5
- + Successfully includes the requested motion blur from a passing car in the background.
- + Strong storytelling with the addition of tools and a more complex street environment.
- + Very realistic lighting and reflection details on both the ground and the car.
- − The composition feels a bit cramped with the crop cutting off the front wheel.
- − The face has slightly softer detail compared to the first model.
Verdict: GPT Image 1.5 is the winner because it successfully incorporated more elements from the prompt, specifically the motion blur of passing cars and a more authentic, cluttered street environment. While GPT Image 1 Mini has a very pleasing cinematic aesthetic, it failed the motion blur requirement and produced a bicycle with significant structural errors in its geometry.
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.”
AI Judge Analysis
GPT Image 1 Mini
- + Excellent rendering of the ornate engraved plate armor with subtle, realistic weathering.
- + Very realistic skin texture and facial anatomy with lifelike eyes.
- + Effective use of shallow depth of field and soft bokeh, creating a painterly cinematic feel.
- − The hair beads requested in the prompt are barely visible or missing in the braids.
- − The lighting is slightly flat compared to the dramatic torchlight requested.
GPT Image 1.5
- + Highly detailed skin texture showing sweat, dirt, and realistic scarring as requested.
- + Includes clear details of small beads in the hair braids and a visible leather strap texture.
- + More dynamic and vibrant torchlight reflections on the metal armor.
- − The bokeh sparks in the background are somewhat distracting and less natural-looking.
- − The armor engraving is slightly less delicate than in the other model.
Verdict: GPT Image 1.5 adhered better to the specific details of the prompt, including the hair beads and the texture of leather straps, while providing a more dynamic and battle-worn appearance. GPT Image 1 Mini has a slightly more realistic, cinematic quality to its processing of light and facial features, but missed the specific bead detail and had less texture on the underlayers.
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.”
AI Judge Analysis
GPT Image 1 Mini
- + Excellent depiction of motion with all four animals 'running' or jumping
- + Very clean composition with distinct, well-defined animals
- + Great adherence to the request for god rays and golden light
- − The fox's front right paw is slightly unnatural in posture
- − The golden retriever's back legs are omitted/hidden in a way that looks slightly disconnected
GPT Image 1.5
- + Expertly captures the 'tumbling together' aspect of the prompt
- + More intricate fur textures and highly expressive facial features
- + Superior lighting effects with beautiful dew sparkles and a visible sunburst
- − The fox has too many visible claws/toes on its right paw
- − The cat's anatomy is slightly distorted due to the 'tumbling' pose
Verdict: GPT Image 1.5 is the winner because it better captures the chaotic, wholesome 'tumbling' requested in the prompt, whereas GPT Image 1 Mini shows the animals running in parallel. GPT Image 1.5 also features more vibrant lighting, more detailed fur, and a more charming interaction between the animals, despite some minor AI paw artifacts.
GPT Image 1 Mini
OpenAI's cost-effective image generation model for when image quality isn't the top priority
GPT Image 1.5
OpenAI's state-of-the-art image generation model with better instruction following and adherence to prompts