ZMIME
Image model comparison · 2 models · Updated Nov 2, 2026

GPT-5 Image vs GLM-Image

Newest: GLM-Image · Widest inputs: GPT-5 Image · Self-hosting: GLM-Image. Not enough arena votes yet for a quality score, so this is a spec comparison.

  1. OpenAI

    GPT-5 Image

    Released Oct 14, 2025

    • Text to image
    • Image editing
    • Arena—
    • From—
    • Max size—
  2. Z.ai (Zhipu)

    GLM-Image

    Released Jan 14, 2026

    • Text to image
    • Image editing
    • Arena1,012
    • From—
    • Max size—
  3. Add a model

    Make it a three-way comparison.

01 — At a glance

Where they differ

Quality is the arena score from blind, side-by-side human votes. Price, length and resolution come from each lab’s own listings.

  • NewestGLM-ImageGPT-5 Image Oct 14, 2025 · GLM-Image Jan 14, 2026
  • Widest inputsGPT-5 ImageGPT-5 Image: Text prompts, Reference images, PDFs · GLM-Image: Text prompts, Reference images
  • Image editingBoth edit imagesTakes a reference image as input: GPT-5 Image yes · GLM-Image yes
  • Self-hostingGLM-ImageDownloadable weights (MIT)
  • Most API hostsGPT-5 ImageGPT-5 Image: 2 · GLM-Image: 1
02 — Side by side

Every spec in one table

Dashes mean the data is not published.

GPT-5 Image vs GLM-Image specifications side by side
SpecificationGPT-5 ImageOpenAIGLM-ImageZ.ai (Zhipu)
Quality (blind human votes)
Text to image arenaElo-style score · higher is better—1,012 ±9#76 of 82 · 4,854 votes
Output
ProducesImagesImages
Inputs
Text promptsYesYes
Reference images (editing)YesYes
Access
WeightsProprietaryOpenMIT
API hosts2 (best)1
ReleasedOct 14, 2025Jan 14, 2026
03 — Questions

Which should you choose?

Which is better, GPT-5 Image or GLM-Image?

Neither model has enough arena votes for a reliable quality score yet, so this page compares specs only. Run the same three or four prompts through each and judge the results.

What is the difference between GPT-5 Image and GLM-Image?

GPT-5 Image is an image model from OpenAI (Oct 14, 2025), taking text prompts, reference images and pdfs and producing images. GLM-Image is an image model from Z.ai (Zhipu) (Jan 14, 2026), taking text prompts and reference images and producing images.

Which is newer?

GPT-5 Image Oct 14, 2025; GLM-Image Jan 14, 2026.

Which can edit an existing image?

Takes a reference image as input: GPT-5 Image yes; GLM-Image yes.

Can I run any of these on my own hardware?

GLM-Image. Downloadable weights (MIT).