Text-to-Image Arena🏆Overall

View overall rankings across text to image AI models.

Apr 22, 2026
4,965,676 votes
17 labs
Lab Rank
Model Score
Rank Spread
1
OpenAI
gpt-image-2 (medium) · Proprietary
1507±9
1
11
2
Google
gemini-3.1-flash-image-preview (nano-banana-2) [web-search] · Proprietary
1271±5
2
22
3
Microsoft AI
mai-image-2 · Proprietary
1183±5
6
67
4
Reve
reve-v1.5 · Proprietary
1177±6
7
69
5
xAI
grok-imagine-image · Proprietary
1170±4
8
710
6
Alibaba
qwen-image-2.0-pro-2026-04-22 · Proprietary
1168±8
9
712
7
Flux
Black Forest Labs
flux-2-max · Proprietary
1166±4
10
811
8
Tencent
Tencent
hunyuan-image-3.0
1151±3
15
1117
9
Bytedance
Bytedance
seedream-4.5 · Proprietary
1142±3
18
1619
10
Recraft
Recraft
recraft-v4 · Proprietary
1109±5
29
2332
11
Ideogram
Ideogram
ideogram-v3-quality · Proprietary
1049±4
42
4242
12
Pruna
p-image · Proprietary
1036±4
43
4344
13
Luma
Luma AI
photon · Proprietary
1035±4
44
4344
14
Runway
runway-gen4 · Proprietary
1026±5
46
4547
15
Leonardo AI
lucid-origin · Proprietary
1013±3
50
4851
16
Z.ai
glm-image
1011±9
51
4751
17
Stability
Stability AI
stable-diffusion-v35-large
938±4
56
5556

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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

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