What is the best AI text-to-image model?

Based on blind community voting, Nano Banana 2 is currently the #1 ranked AI text-to-image model with an Elo rating of 1269. Rankings update in real time as new votes come in.

How are AI text-to-image models ranked on Lumenfall?

Lumenfall Arena ranks AI models through blind community voting. In each matchup, two models generate from the same prompt and voters pick the better result without seeing model names. Votes are processed using TrueSkill, a Bayesian rating algorithm developed by Microsoft Research, that produces a single Elo score reflecting each model's relative quality.

What is an Elo rating for AI models?

An Elo rating is a numerical score representing a model's skill relative to other models. Under the hood, Lumenfall uses TrueSkill, which tracks two values per model: mu (estimated skill) and sigma (uncertainty). The displayed Elo is calculated as 1000 + 10 x (mu - 3*sigma), a conservative lower bound. A model must prove itself consistently across many matchups to earn a high rating.

Best AI Models for Creativity

Creativity · Text-to-Image

Elo rankings from blind votes across 6 challenges in this category.

ImagineArt 1.5 (Preview)

Grok Imagine Image Pro

Stable Diffusion 3.5 Large

Highlights

10 images

Price · Performance

Best models, by

Every ranked model plotted by price against its Elo. The upper-left frontier is the best value: top quality at the lowest cost.

Best Text-to-Image Models by Price

1 model without pricing omitted.

Best AI Models for Creativity

47 models ranked · Last update: July 14, 2026 2:34 AM

#	Model	Price	¢/img	Speed	Elo
1	Nano Banana 2 Google	$$	2.2¢		1269
2	GPT Image 1.5 OpenAI	$	0.9¢		1261
3	Nano Banana Pro Google	$$$	6.7¢		1258
4	FLUX.2 [dev] Turbo fal	$	0.8¢		1257
5	FLUX.2 [dev] Flash fal	$	0.5¢		1253
6	FLUX.2 [pro] Black Forest Labs	$$	1.5¢		1253
7	FLUX.2 [max] Black Forest Labs	$$	3¢		1248
8	GPT Image 2 OpenAI	$$	3.9¢		1245
9	ImagineArt 1.5 (Preview) Vyro AI	$$	3¢	—	1243
10	Seedream 4.5 ByteDance	$$	4¢		1240

11	Recraft V4 Pro Recraft AI	$$$$	25¢		1235
12	FLUX.1 [dev] Black Forest Labs	$$	2.5¢		1234
13	Grok Imagine Image Pro xAI	$$$	7¢		1225
14	Nano Banana Google	$$	3.9¢		1224
15	Recraft V4 Recraft AI	$$	4¢		1223
16	Seedream 4.0 ByteDance	$$	3¢		1221
17	FLUX.2 [dev] Black Forest Labs	$$	1.2¢		1221
18	Z-Image Turbo Alibaba	$	0.5¢		1220
19	Stable Diffusion 3.5 Large Stability AI	$$$	6.5¢		1219
20	GPT Image 1 Mini OpenAI	$	0.5¢		1216
21	Lucid Origin Leonardo AI	$$	2¢	—	1215
22	FLUX.2 [flex] Black Forest Labs	$$$	6¢		1211
23	Seedream 5.0 Lite ByteDance	$$	3.5¢		1210
24	Imagen 4.0 Ultra Generate 001 Google	$$$	6¢		1207
25	Grok Imagine Image xAI	$$	2¢		1207
26	Qwen Image 2512 Alibaba	$$	2¢		1205
27	Nano Banana 2 Lite Google	$$	1.7¢		1204
28	FLUX.1 Kontext [max] Black Forest Labs	$$$	8¢		1200
29	Qwen Image 2.0 Alibaba	$$	3.5¢		1198
30	Wan 2.6 Alibaba	$$	3¢		1197

Google's Nano Banana 2 leads the Creativity rankings with a 76.9% win rate and 1269 Elo, narrowly edging out GPT Image 1.5 (1261 Elo). While FLUX.2 variants dominate the overall top 10 for efficiency, Google and OpenAI models maintain a distinct Elo advantage in this category, with a 12-point gap separating the top leader from the highest-ranked Black Forest Labs model.

Rivalries

Aggregate head-to-head across the arena

FLUX.2 [pro] Stable Diffusion 3.5 Large

58% 3 challenges 42%

Seedream 4.5 Nano Banana Pro

25% 4 challenges 63%

Qwen Image 2512 Grok Imagine Image

56% 2 challenges 44%

Imagen 4.0 Ultra Generate 001 FLUX.2 [dev] Turbo

22% 3 challenges 67%

Think a model is ranked wrong? Cast your vote

Highlighted challenges

GPT Image 2 is first to make it GPT Image 2

Text-to-Image Art Photorealism

The Reversed Rodeo

This competition tests how well AI image models truly understand language versus how much they rely on visual habits from their training data. The prompt is deliberately simple on the surface but devilishly hard in practice. Most models default to the familiar trope of an astronaut riding a horse. By forcing the reversal, we measure three critical capabilities that separate good models from great ones: Strict instruction following (including negations) Accurate subject-object relationships and spatial hierarchy Resistance to strong dataset biases

Text-to-Image 3D Imaging & Modeling Photorealism

Geometric Composition

A spatial-reasoning test. Each object has a precise relationship (inside, on top, behind, seen through the glass), so it measures whether a model follows explicit placement instructions and handles transparency and refraction rather than just approximating the scene.

View all challenges

Keep the arena honest

Cast your vote

Pick winners in blind matchups. Every vote nudges the Elo and shapes these rankings.

Cast Your Vote

Suggest a prompt

Got an idea worth testing? Submit a prompt and watch the models battle it out.

Vote Now

Models · slot A

Creativity · Text-to-Image

Highlights

Best models, by

Best Text-to-Image Models by Price

Best Text-to-Image Models by Speed

Best AI Models for Creativity

Rivalries

Highlighted challenges

The Reversed Rodeo

Geometric Composition

Cast your vote

Suggest a prompt