Text-to-Image Arena🏆Overall

View overall rankings across text to image AI models.

May 12, 2026
5,169,154 votes
17 labs
Lab Rank
Model Score
Rank Spread
1
OpenAI
gpt-image-2 (medium) · Proprietary
1393±7
1
11
2
Google
gemini-3.1-flash-image-preview (nano-banana-2) [web-search] · Proprietary
1268±5
2
22
3
xAI
grok-imagine-image-quality · Proprietary
1223±6
6
56
4
Luma AI
uni-1.1-max · Proprietary
1192±9
7
79
5
Microsoft AI
mai-image-2 · Proprietary
1181±5
9
79
6
Alibaba
qwen-image-2.0-pro-2026-04-22 · Proprietary
1168±8
11
914
7
Reve
reve-v1.5 · Proprietary
1164±7
12
1016
8
Flux
Black Forest Labs
flux-2-max · Proprietary
1164±4
13
1114
9
Tencent
Tencent
hunyuan-image-3.0
1151±3
18
1520
10
Bytedance
Bytedance
seedream-4.5 · Proprietary
1142±3
21
1922
11
Recraft
Recraft
recraft-v4 · Proprietary
1109±4
32
2834
12
Ideogram
Ideogram
ideogram-v3-quality · Proprietary
1049±4
45
4545
13
Pruna
p-image · Proprietary
1035±4
47
4648
14
Runway
runway-gen4 · Proprietary
1027±5
49
4750
15
Leonardo AI
lucid-origin · Proprietary
1013±3
53
5154
16
Z.ai
glm-image
1011±9
54
5054
17
Stability
Stability AI
stable-diffusion-v35-large
938±4
59
5859

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Fraction of Model A Wins for All Non-tied A vs. B Battles

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)