Skip to content
IFAI

Model rankings

1227 models · 5 boards · 2 sources

Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published May 22, 2026

Best images
gpt-image-2 (medium)OpenAI1,389Score
Best open model
hunyuan-image-3.0Tencent1,151Score
Best from China
Top three open models
1hunyuan-image-3.0Tencent · #19 overall1,151
2flux-2-devBlack Forest Labs · #20 overall1,148
3qwen-image-2512Alibaba · #25 overall1,131
This week's changes
Sonic 3.5Speech · #1New
Qwen3.7 MaxIntelligence · #5New
Gemini 3.5 Flash (high)Intelligence · #6New
gemini-3.5-flashCoding · #7New
RankChangeModelScore95% intervalVotes
1—hunyuan-image-3.0OpenTencent1,151±3172,942
2—flux-2-devOpenBlack Forest Labs1,148±557,994
3—qwen-image-2512OpenAlibaba · 1 more variant1,131±469,024
4Newhidream-o1-imageOpenHiDream1,121±93,875
5▼ 1z-image-turboOpenAlibaba1,085±618,097
6▼ 1flux-2-klein-9bOpenBlack Forest Labs1,069±3132,049
7▼ 1qwen-image-prompt-extendOpenAlibaba1,060±3695,838
8▼ 1flux-2-klein-4bOpenBlack Forest Labs1,029±3133,807
9▼ 1glm-imageOpenZ.ai1,011±94,613
10▼ 1flux-1-dev-fp8OpenBlack Forest Labs969±449,221
11▼ 1flux-1-kontext-devOpenBlack Forest Labs940±4216,289
12▼ 1stable-diffusion-v35-largeOpen938±423,396
13▼ 1bagelOpenByteDance898±612,443

Intelligence over time

Each maker's best model at the time on the Artificial Analysis Intelligence Index, by the month it was released.

Gained most · Anthropic +57.2Highest now · Anthropic 64.6Gap between highest and lowest 18.1 ptsTime range Nov 2025 – Nov 2026
64.6Anthropic60.0Google56.9OpenAI50.1Meta46.5Kimi

Arena data comes from the leaderboard dataset it publishes on Hugging Face (CC BY 4.0). Only each board's overall leaderboard is used; scores and ranks are unchanged. dataset · CC BY 4.0

Artificial Analysis data comes from its API (artificialanalysis.ai). Scores are unchanged; ranks follow the scores. artificialanalysis.ai

Open or closed follows the license Arena gives; prices and Artificial Analysis intelligence show only where model names match, otherwise “—”.