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

Based on blind community voting, Seedream 4.5 is currently the #1 ranked AI text-to-image model with an Elo rating of 1282. 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 3D Imaging & Modeling

3D Imaging & Modeling · Text-to-Image

Elo rankings from blind votes across 2 challenges in this category.

1282 #1

Seedream 4.5

1257 #2

Grok Imagine Image Pro

ImagineArt 1.5 (Preview)

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 3D Imaging & Modeling

61 models ranked · Last update: November 12, 2026 3:07 AM

#	Model	Price	¢/img	Elo
1	Seedream 4.5 ByteDance	$$	4¢	1282
2	Grok Imagine Image Pro xAI	$$$	7¢	1257
3	FLUX.2 [dev] Turbo fal	$	0.8¢	1257
4	Nano Banana 2 Google	$$	2.2¢	1254
5	Wan 2.7 Pro Alibaba	$$$	7.5¢	1250
6	GPT Image 2 OpenAI	$$	3.9¢	1248
7	ImagineArt 1.5 (Preview) Vyro AI	$$	3¢	1247
8	FLUX.2 [dev] Flash fal	$	0.5¢	1246
9	Wan 2.7 Alibaba	$$	3¢	1243
10	Wan 2.6 Alibaba	$$	3¢	1239

11	Nano Banana Pro Google	$$$	6.7¢	1239
12	Recraft V4 Pro Recraft AI	$$$$	25¢	1238
13	FLUX.2 [max] Black Forest Labs	$$	3¢	1236
14	Vidu Q2 ShengShu Technology	$$$$	10¢	1236
15	GPT Image 1.5 OpenAI	$	0.9¢	1235
16	Seedream 4.0 ByteDance	$$	3¢	1232
17	FLUX.2 [flex] Black Forest Labs	$$$	6¢	1231
18	Qwen Image 2.0 Alibaba	$$	3.5¢	1221
19	FLUX.1 Kontext [max] Black Forest Labs	$$$	8¢	1221
20	FLUX.2 [klein] 9B Black Forest Labs	$	0.6¢	1220
21	GPT Image 1 Mini OpenAI	$	0.5¢	1219
22	Recraft V4 Recraft AI	$$	4¢	1219
23	Nano Banana 2 Lite Google	$$	1.7¢	1218
24	Wan 2.5 (Preview) Alibaba	$$$	5¢	1217
25	Stable Diffusion 3.5 Large Stability AI	$$$	6.5¢	1215
26	Nano Banana Google	$$	3.9¢	1213
27	Seedream 5.0 Lite ByteDance	$$	3.5¢	1212
28	FLUX.2 [dev] Black Forest Labs	$$	1.2¢	1211
29	GPT Image 1 OpenAI	$$	1.1¢	1206
30	FLUX.2 [pro] Black Forest Labs	$$	1.5¢	1204

Seedream 4.5 leads the category with an Elo of 1282 and a 71.7% win rate, outperforming overall leaderboard frontrunners like Recraft V4 Pro, which drops to 12th place here. Efficiency-focused models also excel in this niche, as the budget-friendly FLUX.2 [dev] Turbo ($0.008/img) maintains a top-three position with an Elo of 1257.

Rivalries

Aggregate head-to-head across the arena

FLUX.2 [dev] Flash Stable Diffusion 3.5 Large

67% 2 challenges 22%

Qwen Image 2512 Grok Imagine Image

56% 2 challenges 44%

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

3D Imaging & Modeling · 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 3D Imaging & Modeling

Rivalries

Highlighted challenges

The Reversed Rodeo

Geometric Composition

Cast your vote

Suggest a prompt