Skip to content
IFAI

Model rankings

1319 models · 5 boards · 2 sources

‹
Week of June 29, 2026
August 10, 2026116 changesAugust 3, 202613 changesJuly 27, 202639 changesJuly 20, 202618 changesJuly 13, 202611 changesJuly 6, 202626 changesJune 29, 202641 changesJune 22, 202612 changesJune 15, 2026184 changesJune 8, 202624 changesJune 1, 202622 changesMay 25, 202617 changes
›
Artificial AnalysisText-to-image arenaArenaText-to-image arena

Text-to-image arena · Anonymous head-to-head votes · Published July 2, 2026

Best images
gpt-image-2 (medium)OpenAI1,386Score
Best open model
ideogram-4.0-qualityIdeogram1,207Score
Best from China
qwen-image-2.0-pro-2026-06-22Alibaba1,192Score
Most voted
gemini-2.5-flash-image-preview (nano-banana)Google802,974Votes
Top three by Score
1gpt-image-2 (medium)OpenAI1,386
2reve-2.0Reve1,272
3gemini-3.1-flash-image-preview (nano-banana-2) [web-search]Google1,270
Top three open models
1ideogram-4.0-qualityIdeogram · #10 overall1,207
2hunyuan-image-3.0Tencent · #22 overall1,151
3flux-2-devBlack Forest Labs · #24 overall1,148
This week's changes
Reve 2.0Image · #2New
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Intelligence · #5New
claude-sonnet-5-thinkingCoding · #5New
Fish Audio S2.1 ProSpeech · #15New
OpenAudio S1 MiniSpeech · #50New
AllOpenClosed
All regionsUSChina
One row per modelAll variants
SortScoreVotes
RankChangeModelScore95% intervalVotes
1—gpt-image-2 (medium)ClosedOpenAI1,386±557,380
2—reve-2.0ClosedReve1,272±711,486
3—gemini-3.1-flash-image-preview (nano-banana-2) [web-search]ClosedGoogle1,270±488,358
4—mai-image-2.5ClosedMicrosoft AI1,257±528,760
5Newgemini-3.1-flash-lite-image (nano-banana-2-lite)ClosedGoogle1,250±96,167
6▼ 1gemini-3-pro-image-preview-2k (nano-banana-pro)ClosedGoogle1,245±4126,398
7▼ 1gpt-image-1.5-high-fidelityClosedOpenAI1,241±3130,444
8▼ 1gemini-3-pro-image-preview (nano-banana-pro)ClosedGoogle1,232±582,562
9▼ 1grok-imagine-image-qualityClosedxAI1,229±536,320
10▼ 1ideogram-4.0-qualityOpenIdeogram1,207±615,512
11▼ 1qwen-image-2.0-pro-2026-06-22ClosedAlibaba1,192±85,764
12▼ 1uni-1.1-maxClosedLuma AI1,188±613,459
13▼ 1mai-image-2ClosedMicrosoft AI1,183±549,031
14▼ 1uni-1.1ClosedLuma AI1,179±518,572
15▼ 1grok-imagine-imageClosedxAI1,174±3201,524
16▼ 1recraft-v4.1-utility-proClosedRecraft1,169±112,510
17▼ 1flux-2-maxClosedBlack Forest Labs1,162±4117,104
18▼ 1grok-imagine-image-proClosedxAI1,161±493,415
19▼ 1flux-2-flexClosedBlack Forest Labs1,156±3148,903
20▼ 1flux-2-proClosedBlack Forest Labs1,155±3163,361
21▼ 1reve-v1.5ClosedReve1,154±429,090
22—hunyuan-image-3.0OpenTencent1,151±3172,742
23▼ 2gemini-2.5-flash-image-preview (nano-banana)ClosedGoogle1,151±3802,974
24▼ 1flux-2-devOpenBlack Forest Labs1,148±560,799
25▼ 1imagen-ultra-4.0-generate-001ClosedGoogle1,148±4387,970
26▼ 1seedream-4.5ClosedByteDance1,146±3215,615
27▼ 1seedream-4-2kClosedByteDance1,141±712,603
28▼ 1wan2.6-t2iClosedAlibaba1,134±3167,229
29▼ 1seedream-5.0-liteClosedByteDance1,133±484,256
30▼ 1recraft-v4.1-proClosedRecraft1,130±112,672
31▼ 1imagen-4.0-generate-001ClosedGoogle1,129±3531,321
32▼ 1qwen-image-2512OpenAlibaba · 1 more variant1,128±481,516
33▼ 1hidream-o1-imageOpenHiDream1,122±521,850
34▼ 1krea-2-mediumClosedKrea1,119±614,533
35—wan2.5-t2i-previewClosedAlibaba1,117±3215,368
36▼ 2seedream-4-falClosedByteDance1,117±711,852
37▼ 1gpt-image-1ClosedOpenAI1,115±3264,690
38▼ 1seedream-4-high-res-falClosedByteDance1,113±3174,944
39Newkrea-2-turboOpenKrea1,112±86,006
40▼ 2recraft-v4ClosedRecraft1,111±486,800
41▼ 2gpt-image-1-miniClosedOpenAI1,109±3163,450
42▼ 2wan2.7-image-proClosedAlibaba1,102±528,662
43▼ 2krea-2-largeClosedKrea1,099±614,290
44▼ 2wan2.7-imageClosedAlibaba1,099±529,010
45▼ 2mai-image-1ClosedMicrosoft AI1,093±494,375
46▼ 2seedream-3ClosedByteDance1,082±536,842
47▼ 2z-image-turboOpenAlibaba1,081±619,603
48▼ 2flux-1-kontext-maxClosedBlack Forest Labs1,074±365,613
49▼ 2flux-2-klein-9bOpenBlack Forest Labs1,069±3142,248
50▼ 2qwen-image-prompt-extendOpenAlibaba1,060±3704,491

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 “—”.