GPT Image 2 OpenAI Qwen Image Edit 2511 Alibaba

Settled by community votes across 2 shared challenges, with an AI judge weighing in on each.

GPT Image 2

28.1 arena score

#3 of 62 in Text-to-Image

Top 3 in Text-to-Image

Skill signature · Text-to-Image

Qwen Image Edit 2511

20.2 arena score

#16 of 32 in Image Editing

Vote tally

Where the votes landed

GPT Image 2

win rate

Ties

Qwen Image Edit 2511

win rate

Shared challenges 2

Challenge by challenge

The strongest take from each model on every shared challenge, with the AI judge's read.

Pose & Character Mashup

Editing

Edit instruction

“Use Image 1 as the exact pose reference and Image 2 as the character reference. Recreate the person/character from Image 2 in the exact dynamic pose and body position from Image 1. Keep the exact face, hair, clothing style/details, and expression from Image 2. Match the lighting and environment of Image 1. The final image must show the character from Image 2 performing the precise action/pose from Image 1 with perfect anatomy and natural integration.”

Source

GPT Image 2

Qwen Image Edit 2511

AI Judge Analysis

GPT Image 2

+ Successfully replicates the exact pose and environment from Image 1.
+ Highly accurate character transfer including facial features, sunglasses, and the specific scarf.
+ Maintains perfect lighting and shadows consistent with the yellow studio setting.

− The fingers on the raised hand are slightly merged.
− The character's hair texture is a bit simplified compared to the source.

Qwen Image Edit 2511

+ Attempts to maintain the resolution of the original images.

− Completely failed the central task by placing the character from Image 2 behind the person from Image 1.
− Did not transfer the character's features into the pose as requested.
− The compositing is very poor with harsh edges and no integration between elements.

Verdict: GPT Image 2 followed the complex instructions perfectly, successfully mapping the person from Image 2 onto the dynamic pose and environment of Image 1. In contrast, Qwen Image Edit 2511 failed to understand the blending instruction, simply overlaying a cutout of the original person from Image 1 on top of the character from Image 2.

Outfit Transfer Challenge

Editing

Edit 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

GPT Image 2

Qwen Image Edit 2511

AI Judge Analysis

GPT Image 2

+ Perfect preservation of the original person's face, hair, and vitiligo markings.
+ Highly accurate replication of the scarf pattern and coat texture from Image 2.
+ Seamless integration of the jewelry (gold watch) and hands in pockets.

− The crop is tighter than the original, losing some of the lower legs shown in the background.

Qwen Image Edit 2511

+ Successfully includes the shoes and full legs as requested by the prompt.
+ Good placement of the clothing on the pose.

− Completely failed to preserve the person's face and hair, replacing them with the man from Image 2.
− Lighting on the face is inconsistent with the beach environment.

Verdict: GPT Image 2 followed the critical instruction to keep the person's face and hair completely unchanged, resulting in a perfect composite of the Subject from Image 1 and the Clothing from Image 2. Qwen Image Edit 2511 failed the primary constraint by replacing the person's identity with the model from the reference image, though it did include the requested shoes.