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.
Ranking Table
| Rank | Model | Score | 95% CI | Votes | Organization | License |
|---|---|---|---|---|---|---|
 gpt-image-2 (medium)OpenAI | 1,512 | +/-8 | 15,127 | OpenAI | Proprietary | |
 gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google | 1,270 | +/-5 | 51,886 | Proprietary | ||
| Nano Banana ProGoogle Deep Mind | 1,244 | +/-4 | 90,321 | Google Deep Mind | Proprietary | |
| 4 | GPT Image 1OpenAI | 1,241 | +/-4 | 95,176 | OpenAI | Proprietary |
| 5 | Nano Banana ProGoogle Deep Mind | 1,232 | +/-5 | 82,636 | Google Deep Mind | Proprietary |
| 6 |  mai-image-2Microsoft AI | 1,184 | +/-5 | 32,001 | Microsoft AI | Proprietary |
| 7 | reve-v1.5Reve | 1,177 | +/-6 | 7,807 | Reve | Proprietary |
| 8 |  Grok Image 1.0xAI | 1,170 | +/-3 | 122,850 | xAI | Proprietary |
| 9 | flux-2-maxBlack Forest Labs | 1,165 | +/-4 | 93,917 | Black Forest Labs | Proprietary |
| 10 | Grok Image 1.0xAI | 1,158 | +/-4 | 77,922 | xAI | Proprietary |
| 11 | flux-2-proBlack Forest Labs | 1,157 | +/-3 | 128,699 | Black Forest Labs | Proprietary |
| 12 | flux-2-flexBlack Forest Labs | 1,156 | +/-4 | 125,703 | Black Forest Labs | Proprietary |
| 13 | Gemini 2.5 Flash Image PreviewGoogle Deep Mind | 1,153 | +/-3 | 750,440 | Google Deep Mind | Proprietary |
| 14 | HunyuanImage-3.0-Instruct腾讯AI实验室 | 1,151 | +/-3 | 172,950 | 腾讯AI实验室 | tencent-hunyuan-community |
| 15 | flux-2-devBlack Forest Labs | 1,149 | +/-5 | 53,660 | Black Forest Labs | flux-non-commercial-license |
| 16 | imagen-ultra-4.0-generate-001Google | 1,148 | +/-4 | 389,670 | Proprietary | |
| 17 | Seedance 2.0字节跳动Seed团队 | 1,143 | +/-3 | 157,984 | 字节跳动Seed团队 | Proprietary |
| 18 |  seedream-4-2kBytedance | 1,140 | +/-7 | 12,627 | Bytedance | Proprietary |
| 19 | Wan2.1-T2V-14B阿里巴巴 | 1,133 | +/-3 | 110,156 | 阿里巴巴 | Proprietary |
| 20 | Qwen-Image-2512阿里巴巴 | 1,133 | +/-4 | 60,982 | 阿里巴巴 | Apache 2.0 |
| 21 | imagen-4.0-generate-001Google | 1,130 | +/-3 | 496,820 | Proprietary | |
| 22 | seedream-5.0-liteBytedance | 1,118 | +/-4 | 50,442 | Bytedance | Proprietary |
| 23 | Wan2.1-T2V-14B阿里巴巴 | 1,117 | +/-3 | 171,115 | 阿里巴巴 | Proprietary |
| 24 | seedream-4-falBytedance | 1,117 | +/-6 | 11,864 | Bytedance | Proprietary |
| 25 | GPT Image 1OpenAI | 1,115 | +/-3 | 265,524 | OpenAI | Proprietary |
| 26 | seedream-4-high-res-falBytedance | 1,112 | +/-3 | 150,218 | Bytedance | Proprietary |
| 27 | recraft-v4Recraft | 1,107 | +/-5 | 49,143 | Recraft | Proprietary |
| 28 | GPT-Image-1-miniOpenAI | 1,104 | +/-3 | 138,903 | OpenAI | Proprietary |
| 29 |  wan2.7-image-proAlibaba | 1,101 | +/-5 | 24,551 | Alibaba | Proprietary |
| 30 | wan2.7-imageAlibaba | 1,098 | +/-5 | 24,781 | Alibaba | Proprietary |
| 31 | mai-image-1Microsoft AI | 1,093 | +/-4 | 94,477 | Microsoft AI | Proprietary |
| 32 | Z-Image-Turbo阿里巴巴 | 1,083 | +/-6 | 15,542 | 阿里巴巴 | Apache 2.0 |
| 33 | seedream-3Bytedance | 1,082 | +/-5 | 36,927 | Bytedance | Proprietary |
| 34 | FLUX.1-Kontext-devBlack Forest Labs | 1,074 | +/-3 | 65,957 | Black Forest Labs | Proprietary |
| 35 | flux-2-klein-9bBlack Forest Labs | 1,068 | +/-3 | 105,189 | Black Forest Labs | flux-non-commercial-license |
| 36 | Qwen Image阿里巴巴 | 1,060 | +/-3 | 666,960 | 阿里巴巴 | Apache 2.0 |
| 37 | FLUX.1-Kontext-devBlack Forest Labs | 1,059 | +/-3 | 332,208 | Black Forest Labs | Proprietary |
| 38 | imagen-3.0-generate-002Google | 1,058 | +/-3 | 361,435 | Proprietary | |
| 39 | Qwen Image阿里巴巴 | 1,057 | +/-2 | 85,120 | 阿里巴巴 | Apache 2.0 |
| 40 | ideogram-v3-qualityIdeogram | 1,049 | +/-4 | 115,280 | Ideogram | Proprietary |
| 41 | p-imagePhuna | 1,035 | +/-4 | 76,677 | Phuna | Proprietary |
| 42 | photonLuma AI | 1,035 | +/-4 | 127,541 | Luma AI | Proprietary |
| 43 | flux-2-klein-4bBlack Forest Labs | 1,027 | +/-3 | 106,945 | Black Forest Labs | Apache 2.0 |
| 44 | runway-gen4Runway | 1,027 | +/-5 | 29,672 | Runway | Proprietary |
| 45 | recraft-v3Recraft | 1,021 | +/-4 | 191,989 | Recraft | Proprietary |
| 46 | flux-1.1-proBlack Forest Labs | 1,016 | +/-3 | 70,460 | Black Forest Labs | Proprietary |
| 47 | ideogram-v2Ideogram | 1,013 | +/-3 | 72,090 | Ideogram | Proprietary |
| 48 | lucid-originLeonardo AI | 1,013 | +/-3 | 286,558 | Leonardo AI | Proprietary |
| 49 | GLM-Image智谱AI | 1,011 | +/-9 | 4,613 | 智谱AI | MIT |
| 50 | Gemini 2.5 Flash Image PreviewGoogle Deep Mind | 975 | +/-3 | 258,222 | Google Deep Mind | Proprietary |
| 51 | flux-1-dev-fp8Black Forest Labs | 969 | +/-4 | 49,221 | Black Forest Labs | Open |
| 52 | DALL·E3OpenAI | 968 | +/-4 | 240,122 | OpenAI | Proprietary |
| 53 | FLUX.1-Kontext-devBlack Forest Labs | 940 | +/-4 | 216,334 | Black Forest Labs | flux-1-dev-non-commercial-license |
| 54 | Stable Diffusion-1.0Stability AI | 938 | +/-4 | 23,396 | Stability AI | Open |
| 55 | bagelBytedance | 898 | +/-6 | 12,461 | Bytedance | Apache 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)
GPT-Image-1.5 High-Fidelity (OpenAI)
Gemini 3 Pro Image Preview 2K (Google)
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)