108 image models, four identical tasks
Compare AI image models
Wan 2.7 Image Pro and Wan 2.7 Image are practically tied at the top of our rating. In user votes, GPT Image 2.5 Sunburst leads. Cheap and good: Muse Image at $0.01 per image.
GraduallyBench
84out of 100
Wan 2.7 Image Pro
practically tied: Wan 2.7 Image (81)
Arena rating
1,427from user votes
GPT Image 2.5 Sunburst
then GPT Image 2.5 Flare (1,399) and GPT Image 2 (1,382)
Cheap and good
$0.01per image via API
Muse Image
rank 4 in GraduallyBench, cheapest of the top ten
What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.
The best AI image models on LMArena
Text to image
Images from a text prompt, rated in anonymous LMArena blind comparisons · higher is better
20 of 21 models
As of November 6, 2026 · Source: LMArena
Image to image
Editing an existing image with a prompt, rated in anonymous LMArena blind comparisons · higher is better
20 of 21 models
As of November 6, 2026 · Source: LMArena
All images at a glance
Number under the image: points in the task (0 to 100)Trophy and violet frame: best image of the taskColumns from left to right: Typography and layout, Product photography, Character and detail, Infographic
n/a
no price known
n/a
no price known
n/a
no price known
$0.01
per image
100 images: $1.00$0.06
per image
100 images: $6.00$0.09
per image
100 images: $9.00n/a
no price known
$0.21
per image
100 images: $21.07n/a
no price known
n/a
no price known
Not rated yet (32)
These models are still missing tasks or the shared evaluation.
- Midjourney V8.2n/a
- Ming-Image-0.1-Designn/a
- WAND-Vega-Image 1.0 Pron/a
- WAND-Vega-Image 1.0 Flashn/a
- WAND-Vega-Image 1.0 Liten/a
- Runway Gen-4 Image Turbon/a
- Leonardo Phoenix 1.0n/a
- Leonardo Lucid Originn/a
- Leonardo Lucid Realismn/a
- Stable Diffusion 3.5 Flashn/a
- Xingliu Star-3n/a
- MiracleVision V6n/a
- Hy Image 3.0Deprecatedn/a
- Mystic 2.5n/a
- Mystic 2.5 Flexiblen/a
- Mystic 2.5 Fluidn/a
- Kling Image O1n/a
- Stable Image Coren/a
- Stable Image Ultran/a
- Midjourney V7n/a
- Niji 7n/a
- HUMAIN Image 1n/a
- Emu3.5-Imagen/a
- NextStep-1.1n/a
- HART-0.7B-1024pxn/a
- Janus-Pro-1Bn/a
- Janus-Pro-7Bn/a
- Show-o2-1.5B-HQn/a
- Kandinsky 3.1n/a
- Anima Base v1.0n/a
- Krea 2 Rawn/a
- HunyuanImage 3.0 Instruct Distiln/a
What does your image volume cost?
| Per month | ||
|---|---|---|
| Muse Image | $0.01 | $10.00 |
| FLUX.2 Klein 9BOpen weightsconfiguration 9B | $0.015 | $15.00 |
| Krea 2 Medium Turboconfiguration Medium Turbo | $0.015 | $15.00 |
| MAI-Image-2.6 FlashPreview | $0.019 | $19.46 |
| MAI-Image-2.5 FlashPreviewconfiguration Flash | $0.02 | $19.97 |
| FLUX.2 Proconfiguration Pro | $0.03 | $30.00 |
| Wan 2.6 Text to Imageconfiguration Text to Image | $0.03 | $30.00 |
| Nano Banana 2 Liteconfiguration Gemini 3.1 Flash Lite Image | $0.034 | $33.60 |
| Recraft V4.1 Utilityconfiguration Utility | $0.035 | $35.00 |
| MAI-Image-2.6Preview | $0.039 | $38.91 |
| HiDream-O1-ImageOpen weights | $0.04 | $40.00 |
| MAI-Image-2.5Preview | $0.048 | $48.13 |
| Grok Imagine Image QualityOutdated | $0.05 | $50.00 |
| FLUX.2 Flexconfiguration Flex | $0.06 | $60.00 |
| Grok Imagine Image 2.0 | $0.06 | $60.00 |
| Ideogram 4.0Open weightsconfiguration Standard | $0.06 | $60.00 |
| Krea 2 Largeconfiguration Large | $0.06 | $60.00 |
| Nano Banana 2configuration Gemini 3.1 Flash Image Preview | $0.067 | $67.00 |
| FLUX.2 Maxconfiguration Max | $0.07 | $70.00 |
| Qwen Image 2.0 Proconfiguration 2026-04-22 | $0.075 | $75.00 |
| HiDream-O1-Image-1.5 | $0.08 | $80.00 |
| Seedream 5.0 Pro | $0.09 | $90.00 |
| Ideogram 4.5Weights unknown | $0.10 | $100 |
| GPT Image 1.5Outdatedconfiguration High | $0.13 | $133 |
| Nano Banana Proconfiguration Gemini 3 Pro Image | $0.13 | $134 |
| GPT Image 2.5 Flare | $0.21 | $211 |
| GPT Image 2.5 Sunburstconfiguration Sunburst | $0.21 | $211 |
| GPT Image 2configuration High | $0.21 | $211 |
28 of 140 models have a representative price per image. The switch “Show models without a price” adds the other 112, without a monthly cost.
Three common questions, three lists
Cheap and good
60+ GraduallyBench points, sorted by price per image
- 1.Muse Image$0.01 · 78
- 2.Krea 2 Medium Turbo$0.015 · 65
- 3.MAI-Image-2.6 Flash$0.019 · 67
- 4.MAI-Image-2.5 Flash$0.02 · 69
- 5.FLUX.2 Pro$0.03 · 65
- 6.Wan 2.6 Text to Image$0.03 · 63
- 7.Nano Banana 2 Lite$0.034 · 71
- 8.Recraft V4.1 Utility$0.035 · 65
- 9.MAI-Image-2.6$0.039 · 68
- 10.MAI-Image-2.5$0.048 · 69
Best arena quality under $0.07
Sorted by LMArena rating
- 1.MAI-Image-2.61,331 · $0.039
- 2.Grok Imagine Image 2.01,317 · $0.06
- 3.Muse Image1,268 · $0.01
- 4.Nano Banana 21,257 · $0.067
- 5.MAI-Image-2.51,253 · $0.048
- 6.Nano Banana 2 Lite1,249 · $0.034
- 7.FLUX.2 Flex1,156 · $0.06
- 8.FLUX.2 Pro1,153 · $0.03
- 9.Krea 2 Large1,115 · $0.06
- 10.HiDream-O1-Image1,115 · $0.04
Open weights
Self-hostable, sorted by API price per image
- 1.FLUX.2 Klein 9B$0.015
- 2.HiDream-O1-Image$0.04
- 3.Ideogram 4.0$0.06
- 4.Anima Base v1.0n/a
- 5.AuraFlow v0.3n/a
- 6.BAGEL-7B-MoTn/a
- 7.Boogu-Image-0.1-Basen/a
- 8.Boogu-Image-0.1-Turbon/a
- 9.Chroma1-Flashn/a
- 10.Chroma1-HDn/a
Popular comparisons
- 1Krea 2 Large vs. FLUX.2 Klein 9B
- 2Krea 2 Medium Turbo vs. Krea 2 Large
- 3GPT Image 2.5 Sunburst vs. Nano Banana Pro
- 4Krea 2 Medium Turbo vs. FLUX.2 Klein 9B
- 5Krea 2 Large vs. Qwen-Image-2.1
- 6Krea 2 Medium Turbo vs. Qwen-Image-2.1
- 7FLUX.2 Flex vs. Qwen-Image-2.1
- 8Nano Banana 2 vs. Nano Banana Pro
- 9Qwen Image 2.0 Pro vs. FLUX.2 Klein 9B
140 important models and configurations
For the full technical profile of every model, browse the AI model directory.
OpenAI
Reve
Black Forest Labs
Alibaba
Luma Labs
Ideogram
Tencent
Stability AI
Meta
SenseTime
Shengshu Technology
Zhipu AI
MiniMax
Tongyi-MAI / Alibaba
Luma AI
LiblibAI / Xingliu
Meitu
Freepik / Magnific
ByteDance / Volcengine
HUMAIN
OpenMOSS
NucleusAI
Meituan
ByteDance Seed
VectorSpaceLab
BAAI
StepFun
Boogu Project
NVIDIA Research
Lodestones
fal.ai
PixArt-Alpha
Alpha-VLLM
MIT HAN Lab
DeepSeek
Show Lab, National University of Singapore
AI Forever
CircleStone Labs and Comfy Org
Krea.ai
Tongyi-MAI, Alibaba
Image model or AI image generator?
An image model is the underlying generation system, such as GPT Image 2.5 Sunburst, Midjourney V8.2, or Nano Banana 2. A generator is the app around one or more models, including its interface, subscription, editing workflow, storage, and usage rights.
Use this page to compare model performance. Use the generator guide to choose a complete product.
Frequently asked questions about the image model comparison
Changelog
Popular comparisons by demand
- Popular comparisons and the further duels on every pair page now follow the computed comparison popularity, with each model's predecessor and successor
Image wall instead of separate leaderboards
- Replaced the leaderboards, gallery matchup, price-quality map, and featured matchups with one image wall: every model, all four tasks, points and rank under each image, price per image
- Added three short answer cards for GraduallyBench, the arena rating, and the cheapest good model with its subscription options
- Opened every image in a large view with its original prompt
Gallery matchup, price-quality map, and GraduallyBench
- Placed the LMArena and GraduallyBench leaderboards side by side
- Added a gallery matchup and an image wall with the archived first outputs of all four tasks
- Added a price-quality map, a cost calculator, and three budget answers
- Renamed the own image test to GraduallyBench and turned popular matchups into cards with scores and prices
Show older versions (6)
35-model roster and re-verified pricing
- Expanded the catalog to 35 models and 595 head-to-head matchups
- Re-verified provider prices and lifecycle notices against current provider pages
GPT Image 2.5 Sunburst and Midjourney V8.2
- Expanded the catalog to 30 models and 435 head-to-head matchups
- Added exact LMArena results for GPT Image 2.5 Sunburst where available
- Kept GPT Image 2 and Midjourney V8.1 samples under their original checkpoints
Complete image model leaderboard
- Added an equal-weight leaderboard for all 28 comparison models
- Combined only the four shared GraduallyBench tasks
- Kept the n = 1 GraduallyBench ranking separate from research benchmarks and preference arenas
Complete matchup coverage and research benchmarks
- Added four shared Gradually rankings from three model-blind orderings of all 28 first outputs
- Integrated exact model results from GenExam, Qwen Image Bench, and WISE Verified
- Kept n = 1 GraduallyBench rankings, academic benchmarks, and preference arenas visibly separate
FAQ, changelog, and internal links
- Added an FAQ that quantifies shared arena coverage and explains data gaps
- Added this changelog so material updates remain visible
- Added the hub and all matchup pages to navigation, the sitemap, and related comparisons
Initial release
- Published 28 current image models and 378 head-to-head matchups
- Kept text-to-image generation and image editing in separate benchmark series
- Combined pricing, specifications, sources, and documented sample images