DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
HomeOverall LeaderboardText-to-Image Arena Leaderboard

LMArena Tracks

Text GenerationCodingMathImage EditText-to-VideoImage-to-Video

Text-to-Image Arena Leaderboard

The latest AI text-to-image model leaderboard based on Text-to-Image Arena anonymous user voting. Covers Elo scores, confidence intervals, and vote counts for GPT-Image, FLUX, Midjourney, DALL-E, and more.

Top Model

GPT-image-2 (medium)

Top Score

1,389

Model Count

63

Data version

2026年05月22日

Data source: LM Arena

About This Leaderboard

This leaderboard ranks AI text-to-image models by generation quality. Data comes from LMArena's Text-to-Image Arena track, evaluated through anonymous blind testing by real users.

Methodology Overview

Blind testing: Users submit text prompts, two anonymous models generate images, and users vote for the better result.

Elo scoring: Based on the Bradley-Terry model, scientifically measuring each model's relative strength in text-to-image generation.

Origin:AllChina
Leaderboard snapshot month:

Ranking Table

RankModelScore95% CIVotesOrganizationLicense
OpenAIGPT-image-2 (medium)OpenAI

Data is for reference only. Official sources are authoritative. Click model names to view DataLearner model profiles.

2026-05 Market Signals

Current Best (SOTA)

01

GPT-Image-1.5 High-Fidelity (OpenAI)

02

Gemini 3 Pro Image Preview 2K (Google)

03

Gemini 3 Pro Image Preview (Google)

Best China Model

HunyuanImage-3.0 (腾讯)

Seedream-4.5 (字节跳动)

Qwen-Image-2512 (阿里)

Best Open Model

  • •Qwen-Image-2512 (阿里)
  • •Z-Image-Turbo (阿里)
  • •GLM-Image (智谱)

FAQ

01

What is the difference between text-to-image and image editing?

Text-to-image creates a new image from a prompt. Image editing modifies an existing image, which is better for local changes, style transfer, and production refinements.

02

Which models are suitable for commercial poster design?

For commercial posters, prioritize models with strong text rendering, controllable composition, high-resolution output, and license terms that fit your use case. The top-ranked model may not be the best option if typography or brand control matters most.

03

What is prompt engineering?

Prompt engineering means structuring the text input to guide the generated image. Clear descriptions of subject, style, lighting, composition, and constraints usually improve quality and alignment.

Text-to-Image

Diverse generation scenarios: Covers photorealistic scenes, artistic illustration, product design, character creation, and more.

DataLearner provides in-depth analysis on top of the raw data, linking leaderboard models to the DataLearner model database so you can quickly access model details, API pricing, benchmark scores, and more.

1,389
+/-7
39,046
OpenAI
Proprietary
GoogleGemini 3.1 Flash Image PreviewGoogle1,270+/-569,504GoogleProprietary
Google Deep MindNano Banana ProGoogle Deep Mind1,243+/-4108,214Google Deep MindProprietary
4OpenAIGPT Image 1OpenAI1,241+/-4112,907OpenAIProprietary
5Google Deep MindNano Banana ProGoogle Deep Mind1,232+/-582,646Google Deep MindProprietary
6xAIGrok Image 1.0xAI1,228+/-618,156xAIProprietary
7LUUni 1.1 MaxLuma AI1,192+/-77,852Luma AIProprietary
8Microsoft AIMAI Image 2Microsoft AI1,182+/-547,011Microsoft AIProprietary
9LUUni 1.1Luma AI1,176+/-78,849Luma AIProprietary
10xAIGrok Image 1.0xAI1,173+/-3164,236xAIProprietary
11RERecraft v4.1 Utility ProRecraft1,169+/-112,512RecraftProprietary
12阿里Qwen-Image-2.0阿里巴巴1,168+/-85,159阿里巴巴Proprietary
13BLFLUX 2 MaxBlack Forest Labs1,164+/-4110,207Black Forest LabsProprietary
14xAIGrok Image 1.0xAI1,161+/-492,852xAIProprietary
15REReve v1.5Reve1,157+/-613,786ReveProprietary
16BLFLUX 2 ProBlack Forest Labs1,156+/-3145,814Black Forest LabsProprietary
17BLFLUX 2 FlexBlack Forest Labs1,155+/-4141,893Black Forest LabsProprietary
18Google Deep MindGemini 2.5 Flash Image PreviewGoogle Deep Mind1,152+/-3777,940Google Deep MindProprietary
19腾讯HunyuanImage-3.0-Instruct腾讯AI实验室1,151+/-3172,942腾讯AI实验室tencent-hunyuan-community
20BLFLUX 2 DevBlack Forest Labs1,148+/-557,994Black Forest Labsflux-non-commercial-license
21GoogleImagen Ultra 4.0Google1,148+/-4389,629GoogleProprietary
22字节Seedance 2.0字节跳动Seed团队1,144+/-3187,049字节跳动Seed团队Proprietary
23BytedanceSeedream 4 2KBytedance1,140+/-712,626BytedanceProprietary
24阿里Wan2.1-T2V-14B阿里巴巴1,134+/-3144,077阿里巴巴Proprietary
25阿里Qwen-Image-2512阿里巴巴1,131+/-469,024阿里巴巴Apache 2.0
26RERecraft v4.1 ProRecraft1,130+/-112,677RecraftProprietary
27GoogleImagen 4.0Google1,130+/-3515,441GoogleProprietary
28BytedanceSeedream 5.0 LiteBytedance1,125+/-466,899BytedanceProprietary
29HIHiDream O1 ImageHiDream1,121+/-93,875HiDreamMIT
30BytedanceSeedream 4 (FAL)Bytedance1,117+/-711,861BytedanceProprietary
31阿里Wan2.1-T2V-14B阿里巴巴1,116+/-3192,875阿里巴巴Proprietary
32阿里Qwen-Image-2.0阿里巴巴1,116+/-552,358阿里巴巴Proprietary
33OpenAIGPT Image 1OpenAI1,115+/-3265,504OpenAIProprietary
34BytedanceSeedream 4 High Res (FAL)Bytedance1,113+/-3167,994BytedanceProprietary
35RERecraft v4Recraft1,109+/-467,787RecraftProprietary
36OpenAIGPT-Image-1-miniOpenAI1,108+/-3156,487OpenAIProprietary
37AlibabaWan2.7 Image ProAlibaba1,104+/-528,420AlibabaProprietary
38AlibabaWan2.7 ImageAlibaba1,099+/-528,699AlibabaProprietary
39Microsoft AIMAI Image 1Microsoft AI1,093+/-494,470Microsoft AIProprietary
40阿里Z-Image-Turbo阿里巴巴1,085+/-618,097阿里巴巴Apache 2.0
41BytedanceSeedream 3Bytedance1,082+/-536,922BytedanceProprietary
42BLFLUX.1-Kontext-dev (max)Black Forest Labs1,074+/-365,886Black Forest LabsProprietary
43BLFLUX 2 Klein 9BBlack Forest Labs1,069+/-3132,049Black Forest Labsflux-non-commercial-license
44阿里Qwen Image阿里巴巴1,060+/-3695,838阿里巴巴Apache 2.0
45BLFLUX.1-Kontext-devBlack Forest Labs1,059+/-3332,136Black Forest LabsProprietary
46GoogleImagen 3.0 (002)Google1,058+/-3361,365GoogleProprietary
47阿里Qwen Image阿里巴巴1,057+/-285,107阿里巴巴Apache 2.0
48IDIdeogram v3 QualityIdeogram1,049+/-4115,284IdeogramProprietary
49LUPhoton (Luma)Luma AI1,035+/-4127,549Luma AIProprietary
50PHp-imagePhuna1,035+/-495,853PhunaProprietary
51BLFLUX 2 Klein 4BBlack Forest Labs1,029+/-3133,807Black Forest LabsApache 2.0
52RUrunway-gen4Runway1,026+/-545,413RunwayProprietary
53RErecraft-v3Recraft1,021+/-4191,995RecraftProprietary
54BLflux-1.1-proBlack Forest Labs1,016+/-370,460Black Forest LabsProprietary
55LElucid-originLeonardo AI1,013+/-3286,548Leonardo AIProprietary
56IDideogram-v2Ideogram1,013+/-372,090IdeogramProprietary
57智谱GLM-Image智谱AI1,011+/-94,613智谱AIMIT
58Google Deep MindGemini 2.5 Flash Image PreviewGoogle Deep Mind975+/-3258,170Google Deep MindProprietary
59BLflux-1-dev-fp8Black Forest Labs969+/-449,221Black Forest LabsOpen
60OpenAIDALL·E3OpenAI968+/-4240,071OpenAIProprietary
61BLFLUX.1-Kontext-devBlack Forest Labs940+/-4216,289Black Forest Labsflux-1-dev-non-commercial-license
62STStable Diffusion-1.0Stability AI938+/-423,396Stability AIOpen
63BytedanceBAGELBytedance898+/-612,443BytedanceApache 2.0
04

How large is the gap between open and closed image models?

The gap has narrowed, especially for customizable open models. Closed models can still lead on instruction following, typography, and detail consistency, while open models are attractive for local deployment, tuning, and cost control.