Skip to content
IFAI

Model rankings

1203 models · 5 boards · 2 sources

‹
Week of May 4, 2026
June 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changesMay 25, 202617 changesMay 18, 202616 changesMay 11, 202665 changesMay 4, 202616 changesApril 27, 202624 changesApril 20, 202627 changesApril 13, 202637 changesApril 6, 202641 changesMarch 30, 2026230 changes
›
Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published May 6, 2026

Best images
gpt-image-2 (medium)OpenAI1,398Score
Best open model
hunyuan-image-3.0Tencent1,151Score
Best from China
qwen-image-2.0-pro-2026-04-22Alibaba1,167Score
Most voted
gemini-2.5-flash-image-preview (nano-banana)Google766,253Votes
Top three by Score
1gpt-image-2 (medium)OpenAI1,398
2gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google1,268
3gemini-3-pro-image-preview-2k (nano-banana-pro)Google1,242
Top three open models
1hunyuan-image-3.0Tencent · #18 overall1,151
2flux-2-devBlack Forest Labs · #19 overall1,149
3qwen-image-2512Alibaba · #24 overall1,131
This week's changes
StepAudio 2.5 TTSSpeech · #3New
Bach-1.0 PreviewVideo · #7New
SIMBA 3.0Speech · #7New
qwen3.6-max-previewCoding · #9New
Peanut (Open Weights Coming Soon)Image · #9New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreVotes
RankChangeModelScore95% intervalVotes
1—gpt-image-2 (medium)ClosedOpenAI1,398±831,058
2—gemini-3.1-flash-image-preview (nano-banana-2) [web-search]ClosedGoogle1,268±561,429
3—gemini-3-pro-image-preview-2k (nano-banana-pro)ClosedGoogle1,242±4100,485
4—gpt-image-1.5-high-fidelityClosedOpenAI1,240±4105,280
5—gemini-3-pro-image-preview (nano-banana-pro)ClosedGoogle1,232±582,641
6Newgrok-imagine-image-qualityClosedxAI1,223±611,006
7Newuni-1.1-maxClosedLuma AI1,193±122,346
8Newuni-1.1ClosedLuma AI1,190±112,662
9▼ 3mai-image-2ClosedMicrosoft AI1,181±539,905
10▼ 3reve-v1.5ClosedReve1,177±67,818
11▼ 3grok-imagine-imageClosedxAI1,172±3146,815
12▼ 3qwen-image-2.0-pro-2026-04-22ClosedAlibaba1,167±85,108
13▼ 3flux-2-maxClosedBlack Forest Labs1,163±4102,996
14▼ 3grok-imagine-image-proClosedxAI1,160±488,133
15▼ 3flux-2-proClosedBlack Forest Labs1,156±4138,343
16▼ 3flux-2-flexClosedBlack Forest Labs1,155±4134,528
17▼ 3gemini-2.5-flash-image-preview (nano-banana)ClosedGoogle1,152±3766,253
18▼ 3hunyuan-image-3.0OpenTencent1,151±3172,953
19▼ 3flux-2-devOpenBlack Forest Labs1,149±557,622
20▼ 3imagen-ultra-4.0-generate-001ClosedGoogle1,148±4389,669
21▼ 3seedream-4.5ClosedByteDance1,142±3174,859
22▼ 3seedream-4-2kClosedByteDance1,140±712,627
23▼ 2wan2.6-t2iClosedAlibaba1,134±4130,067
24▼ 4qwen-image-2512OpenAlibaba · 1 more variant1,131±463,445
25▼ 3imagen-4.0-generate-001ClosedGoogle1,130±3507,745
26▼ 2seedream-5.0-liteClosedByteDance1,120±559,820
27▼ 2qwen-image-2.0-2026-03-03ClosedAlibaba1,117±544,643
28▼ 2seedream-4-falClosedByteDance1,116±611,864
29▼ 6wan2.5-t2i-previewClosedAlibaba1,116±3183,324
30▼ 3gpt-image-1ClosedOpenAI1,115±3265,539
31▼ 3seedream-4-high-res-falClosedByteDance1,112±3160,409
32▼ 3recraft-v4ClosedRecraft1,109±560,045
33▼ 3gpt-image-1-miniClosedOpenAI1,108±3149,037
34▼ 3wan2.7-image-proClosedAlibaba1,102±528,136
35▼ 3wan2.7-imageClosedAlibaba1,098±528,414
36▼ 3mai-image-1ClosedMicrosoft AI1,093±494,476
37▼ 3z-image-turboOpenAlibaba1,084±616,739
38▼ 3seedream-3ClosedByteDance1,082±536,923
39▼ 3flux-1-kontext-maxClosedBlack Forest Labs1,074±365,948
40▼ 3flux-2-klein-9bOpenBlack Forest Labs1,069±4120,265
41▼ 3qwen-image-prompt-extendOpenAlibaba1,061±3683,788
42▼ 3flux-1-kontext-proClosedBlack Forest Labs1,059±3332,204
43▼ 3imagen-3.0-generate-002ClosedGoogle1,058±3361,414
44▼ 3ideogram-v3-qualityClosedIdeogram1,049±4115,279
45▼ 2photonClosedLuma AI1,035±4127,557
46▼ 4p-imageClosed1,035±487,747
47▼ 3flux-2-klein-4bOpenBlack Forest Labs1,028±4122,175
48▼ 3runway-gen4ClosedRunway1,026±538,909
49▼ 3recraft-v3ClosedRecraft1,021±4192,013
50▼ 3flux-1.1-proClosedBlack Forest Labs1,016±370,460

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 “—”.