Skip to content
IFAI

Model rankings

1239 models · 5 boards · 2 sources

‹
Week of May 25, 2026
July 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changesJune 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 changes
›
Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published May 26, 2026

Best images
gpt-image-2 (medium)OpenAI1,388Score
Best open model
hunyuan-image-3.0Tencent1,151Score
Best from China
qwen-image-2.0-pro-2026-04-22Alibaba1,168Score
Most voted
gemini-2.5-flash-image-preview (nano-banana)Google779,780Votes
Top three by Score
1gpt-image-2 (medium)OpenAI1,388
2gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google1,271
3mai-image-2.5-previewMicrosoft AI1,254
Top three open models
1hunyuan-image-3.0Tencent · #20 overall1,151
2flux-2-devBlack Forest Labs · #21 overall1,148
3qwen-image-2512Alibaba · #26 overall1,130
This week's changes
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Intelligence · #1New
qwen3.7-max-20260517Coding · #3New
xAI Text to SpeechSpeech · #5New
Recraft V4.1 Utility ProImage · #6New
Fun-Realtime-TTS-PreviewSpeech · #6New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreVotes
RankChangeModelScore95% intervalVotes
1—gpt-image-2 (medium)ClosedOpenAI1,388±640,350
2—gemini-3.1-flash-image-preview (nano-banana-2) [web-search]ClosedGoogle1,271±570,937
3Newmai-image-2.5-previewClosedMicrosoft AI1,254±85,264
4▼ 1gemini-3-pro-image-preview-2k (nano-banana-pro)ClosedGoogle1,244±4109,593
5▼ 1gpt-image-1.5-high-fidelityClosedOpenAI1,241±4114,188
6▼ 1gemini-3-pro-image-preview (nano-banana-pro)ClosedGoogle1,232±582,642
7▼ 1grok-imagine-image-qualityClosedxAI1,228±619,400
8▼ 1uni-1.1-maxClosedLuma AI1,192±78,945
9▼ 1mai-image-2ClosedMicrosoft AI1,182±548,294
10▼ 1uni-1.1ClosedLuma AI1,176±710,027
11▼ 1grok-imagine-imageClosedxAI1,174±3166,767
12▼ 1recraft-v4.1-utility-proClosedRecraft1,169±112,513
13▼ 1qwen-image-2.0-pro-2026-04-22ClosedAlibaba1,168±85,170
14▼ 1flux-2-maxClosedBlack Forest Labs1,163±4111,466
15▼ 1grok-imagine-image-proClosedxAI1,162±492,985
16▼ 1reve-v1.5ClosedReve1,155±614,926
17▼ 1flux-2-proClosedBlack Forest Labs1,155±3147,144
18▼ 1flux-2-flexClosedBlack Forest Labs1,154±4143,156
19▼ 1gemini-2.5-flash-image-preview (nano-banana)ClosedGoogle1,152±3779,780
20▼ 1hunyuan-image-3.0OpenTencent1,151±3172,943
21▼ 1flux-2-devOpenBlack Forest Labs1,148±558,015
22▼ 1imagen-ultra-4.0-generate-001ClosedGoogle1,148±4389,625
23▼ 1seedream-4.5ClosedByteDance1,143±3189,002
24▼ 1seedream-4-2kClosedByteDance1,141±712,625
25▼ 1wan2.6-t2iClosedAlibaba1,134±3145,754
26▼ 1qwen-image-2512OpenAlibaba1,130±470,034
27▼ 1recraft-v4.1-proClosedRecraft1,130±112,676
28▼ 1imagen-4.0-generate-001ClosedGoogle1,130±3516,873
29▼ 1seedream-5.0-liteClosedByteDance1,127±468,136
30▼ 1hidream-o1-imageOpenHiDream1,121±85,108
31▼ 1seedream-4-falClosedByteDance1,117±611,861
32▼ 1wan2.5-t2i-previewClosedAlibaba1,116±3194,440
33▼ 1qwen-image-2.0-2026-03-03ClosedAlibaba1,115±453,634
34▼ 1gpt-image-1ClosedOpenAI1,115±3265,512
35▼ 1seedream-4-high-res-falClosedByteDance1,113±3169,280
36▼ 1recraft-v4ClosedRecraft1,110±469,221
37▼ 1gpt-image-1-miniClosedOpenAI1,108±3157,830
38▼ 1wan2.7-image-proClosedAlibaba1,103±528,492
39▼ 1wan2.7-imageClosedAlibaba1,099±528,795
40▼ 1mai-image-1ClosedMicrosoft AI1,093±494,475
41▼ 1z-image-turboOpenAlibaba1,084±618,267
42▼ 1seedream-3ClosedByteDance1,082±536,920
43▼ 1flux-1-kontext-maxClosedBlack Forest Labs1,074±365,887
44▼ 1flux-2-klein-9bOpenBlack Forest Labs1,069±3133,827
45▼ 1qwen-image-prompt-extendOpenAlibaba1,060±3697,759
46▼ 1flux-1-kontext-proClosedBlack Forest Labs1,059±3332,137
47▼ 1imagen-3.0-generate-002ClosedGoogle1,058±3361,365
48▼ 1qwen-imageOpenAlibaba1,057±285,106
49▼ 1ideogram-v3-qualityClosedIdeogram1,049±4115,282
50▼ 1photonClosedLuma AI1,035±4127,551

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 “—”.