Skip to content
IFAI

Model rankings

262 models · 2 boards · 2 sources

‹
Week of March 3, 2025
April 14, 20259 changesApril 7, 20255 changesMarch 31, 20253 changesMarch 24, 202512 changesMarch 17, 20254 changesMarch 10, 202511 changesMarch 3, 202513 changesFebruary 24, 202525 changesFebruary 17, 2025February 10, 2025February 3, 2025January 27, 2025
›
Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published March 3, 2025

Best images
imagen-3.0-generate-002Google1,090Score
Best open model
flux-1-dev-fp8Black Forest Labs976Score
Most voted
imagen-3.0-generate-002Google47,674Votes
Top three by Score
1imagen-3.0-generate-002Google1,090
2recraft-v3Recraft1,028
3photonLuma AI1,023
Top three open models
1flux-1-dev-fp8Black Forest Labs · #7 overall976
2stable-diffusion-v35-largeStability AI · #8 overall945
This week's changes
Claude 3.7 Sonnet (Extended Thinking)Intelligence · #4New
Qwen2 Instruct 72BIntelligence · #39New
Claude 3 SonnetIntelligence · #45New
Qwen2.5 Coder Instruct 7BIntelligence · #51New
Claude 2.1Intelligence · #53New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreVotes
RankChangeModelScore95% intervalVotes
1—flux-1-dev-fp8OpenBlack Forest Labs976±339,128
2—stable-diffusion-v35-largeOpenStability AI945±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 “—”.