Skip to content
IFAI

Model rankings

291 models · 2 boards · 2 sources

‹
Week of March 31, 2025
May 12, 20256 changesMay 5, 20255 changesApril 28, 2025April 21, 20254 changesApril 14, 20259 changesApril 7, 20255 changesMarch 31, 20253 changesMarch 24, 202512 changesMarch 17, 20254 changesMarch 10, 202511 changesMarch 3, 202513 changesFebruary 24, 202525 changes
›
Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published April 5, 2025

Best images
imagen-3.0-generate-002Google1,088Score
Best open model
flux-1-dev-fp8Black Forest Labs974Score
Most voted
imagen-3.0-generate-002Google74,125Votes
Top three by Score
1imagen-3.0-generate-002Google1,088
2recraft-v3Recraft1,025
3photonLuma AI1,021
Top three open models
1flux-1-dev-fp8Black Forest Labs · #7 overall974
2stable-diffusion-v35-largeStability AI · #8 overall943
This week's changes
Gemini 2.5 Pro Experimental (Mar' 25)Intelligence · #1New
Gemini 2.0 Flash Thinking Experimental (Jan '25)Intelligence · #9New
GPT-4o (March 2025, chatgpt-4o-latest)Intelligence · #11Up 9
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreVotes
RankChangeModelScore95% intervalVotes
1—flux-1-dev-fp8OpenBlack Forest Labs974±250,585
2—stable-diffusion-v35-largeOpenStability AI943±324,050

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 “—”.