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-VideoText-to-Image

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

1,512

Model Count

55

Data version

2026年04月19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.

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.

Origin:AllChina
Leaderboard snapshot month:

Ranking Table

RankModelScore95% CIVotesOrganizationLicense
OpenAIgpt-image-2 (medium)OpenAI1,512+/-815,127OpenAIProprietary
Googlegemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google1,270+/-551,886GoogleProprietary
Google Deep MindNano Banana ProGoogle Deep Mind1,244+/-490,321Google Deep MindProprietary
4OpenAIGPT Image 1OpenAI1,241+/-495,176OpenAIProprietary
5Google Deep MindNano Banana ProGoogle Deep Mind1,232+/-582,636Google Deep MindProprietary
6Microsoft AImai-image-2Microsoft AI1,184+/-532,001Microsoft AIProprietary
7REreve-v1.5Reve1,177+/-67,807ReveProprietary
8xAIGrok Image 1.0xAI1,170+/-3122,850xAIProprietary
9BLflux-2-maxBlack Forest Labs1,165+/-493,917Black Forest LabsProprietary
10xAIGrok Image 1.0xAI1,158+/-477,922xAIProprietary
11BLflux-2-proBlack Forest Labs1,157+/-3128,699Black Forest LabsProprietary
12BLflux-2-flexBlack Forest Labs1,156+/-4125,703Black Forest LabsProprietary
13Google Deep MindGemini 2.5 Flash Image PreviewGoogle Deep Mind1,153+/-3750,440Google Deep MindProprietary
14腾讯HunyuanImage-3.0-Instruct腾讯AI实验室1,151+/-3172,950腾讯AI实验室tencent-hunyuan-community
15BLflux-2-devBlack Forest Labs1,149+/-553,660Black Forest Labsflux-non-commercial-license
16Googleimagen-ultra-4.0-generate-001Google1,148+/-4389,670GoogleProprietary
17字节Seedance 2.0字节跳动Seed团队1,143+/-3157,984字节跳动Seed团队Proprietary
18Bytedanceseedream-4-2kBytedance1,140+/-712,627BytedanceProprietary
19阿里Wan2.1-T2V-14B阿里巴巴1,133+/-3110,156阿里巴巴Proprietary
20阿里Qwen-Image-2512阿里巴巴1,133+/-460,982阿里巴巴Apache 2.0
21Googleimagen-4.0-generate-001Google1,130+/-3496,820GoogleProprietary
22Bytedanceseedream-5.0-liteBytedance1,118+/-450,442BytedanceProprietary
23阿里Wan2.1-T2V-14B阿里巴巴1,117+/-3171,115阿里巴巴Proprietary
24Bytedanceseedream-4-falBytedance1,117+/-611,864BytedanceProprietary
25OpenAIGPT Image 1OpenAI1,115+/-3265,524OpenAIProprietary
26Bytedanceseedream-4-high-res-falBytedance1,112+/-3150,218BytedanceProprietary
27RErecraft-v4Recraft1,107+/-549,143RecraftProprietary
28OpenAIGPT-Image-1-miniOpenAI1,104+/-3138,903OpenAIProprietary
29Alibabawan2.7-image-proAlibaba1,101+/-524,551AlibabaProprietary
30Alibabawan2.7-imageAlibaba1,098+/-524,781AlibabaProprietary
31Microsoft AImai-image-1Microsoft AI1,093+/-494,477Microsoft AIProprietary
32阿里Z-Image-Turbo阿里巴巴1,083+/-615,542阿里巴巴Apache 2.0
33Bytedanceseedream-3Bytedance1,082+/-536,927BytedanceProprietary
34BLFLUX.1-Kontext-devBlack Forest Labs1,074+/-365,957Black Forest LabsProprietary
35BLflux-2-klein-9bBlack Forest Labs1,068+/-3105,189Black Forest Labsflux-non-commercial-license
36阿里Qwen Image阿里巴巴1,060+/-3666,960阿里巴巴Apache 2.0
37BLFLUX.1-Kontext-devBlack Forest Labs1,059+/-3332,208Black Forest LabsProprietary
38Googleimagen-3.0-generate-002Google1,058+/-3361,435GoogleProprietary
39阿里Qwen Image阿里巴巴1,057+/-285,120阿里巴巴Apache 2.0
40IDideogram-v3-qualityIdeogram1,049+/-4115,280IdeogramProprietary
41PHp-imagePhuna1,035+/-476,677PhunaProprietary
42LUphotonLuma AI1,035+/-4127,541Luma AIProprietary
43BLflux-2-klein-4bBlack Forest Labs1,027+/-3106,945Black Forest LabsApache 2.0
44RUrunway-gen4Runway1,027+/-529,672RunwayProprietary
45RErecraft-v3Recraft1,021+/-4191,989RecraftProprietary
46BLflux-1.1-proBlack Forest Labs1,016+/-370,460Black Forest LabsProprietary
47IDideogram-v2Ideogram1,013+/-372,090IdeogramProprietary
48LElucid-originLeonardo AI1,013+/-3286,558Leonardo AIProprietary
49智谱GLM-Image智谱AI1,011+/-94,613智谱AIMIT
50Google Deep MindGemini 2.5 Flash Image PreviewGoogle Deep Mind975+/-3258,222Google Deep MindProprietary
51BLflux-1-dev-fp8Black Forest Labs969+/-449,221Black Forest LabsOpen
52OpenAIDALL·E3OpenAI968+/-4240,122OpenAIProprietary
53BLFLUX.1-Kontext-devBlack Forest Labs940+/-4216,334Black Forest Labsflux-1-dev-non-commercial-license
54STStable Diffusion-1.0Stability AI938+/-423,396Stability AIOpen
55BytedancebagelBytedance898+/-612,461BytedanceApache 2.0

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

2026-04 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

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.
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.
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.
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.