The Open Weights
LatestModelsLeaderboardsCompanies
Subscribe
The Open Weights

The daily record of open-source AI. New model releases, leaderboards, and what's coming next — written for people who ship.

Refreshed every 12 hours

Discover

  • Latest releases
  • New today
  • Trending models

Browse

  • All models
  • Companies
  • Categories
  • Leaderboards

About

  • About
  • Editorial policy
  • RSS feed
  • Newsletter

© 2026 The Open Weights. An independent publication.

PrivacyTermsSMSAggregated by Claude · curated by humans.

Leaderboard

Text-to-Image

Human-preference Elo for text-to-image models from the Artificial Analysis Arena — open-weight and proprietary, ranked head-to-head.

Source: Artificial Analysis Arena · Updated Sep 17, 2026 · 20 models
LLM IntelligenceText-to-ImageImage EditingText-to-VideoImage-to-VideoText-to-SpeechOpen LLMMost DownloadedCommunity Favorites
#ModelElo
1
FLUX.2 [dev]
Black Forest Labs
1,000
2
FLUX.2 [dev] Turbo
Fal
999
3
HiDream-O1-Image
HiDream
978
4
HunyuanImage 3.0 Instruct
Tencent
966
5
HunyuanImage 3.0
Tencent
945
6
FLUX.2 [klein] 9B
Black Forest Labs
939
7
ERNIE Image Turbo
Baidu
921
8
ERNIE Image
Baidu
912
9
FLUX.2 [klein] Base 9B
Black Forest Labs
902
10
GLM-Image
Zhipu AI
889
11
HunyuanImage 2.1
Tencent
886
12
Qwen Image
Qwen · Alibaba
885
13
HiDream-O1-Image-Dev
HiDream
882
14
HiDream-I1-Dev
HiDream
873
15
HiDream-I1-Fast
HiDream
869
16
FLUX.2 [klein] 4B
Black Forest Labs
864
17
FLUX.1 Krea [dev]
Black Forest Labs
844
18
FLUX.1 [dev]
Black Forest Labs
842
19
Stable Diffusion 3.5 Large
Stability AI
839
20
Stable Diffusion 3 Large
Stability AI
838

Leaderboard data is cached from Artificial Analysis Arena and refreshed every 12 hours. Scores shown are for reference; see the source for full methodology.