Leaderboards
Models
Blog
Methodology
DesignArena by Intelligence
Code
Office
Image
Video
Audio
Code
Office
Image
Video
Audio
DesignArena by Intelligence

Overall Preference vs Speed

Generation Time (slower →)Elo Rating (better →)

Overall Preference vs Price

Price per 1M Tokens (Log scale)Elo Rating (better →)

DesignArena

The largest crowdsourced benchmark for AI-generated design.

© 2026 DesignArena by Intelligence

Leaderboards

  • All Leaderboards
  • Overall Agentic
  • Overall HTML

Build with AI

  • Start Building
  • Website
  • Web Apps
  • Fullstack
  • Mobile App
  • Game
  • 3D Asset
  • Image
  • Video
  • SVG
  • Slides
  • Text-to-Speech

Code Leaderboards

  • Website (HTML, Non-Agentic)
  • Website (Frontend, Agentic)
  • Website (Fullstack, Agentic)
  • Builder
  • Image to HTML
  • Video to Website
  • Image to Frontend
  • Game Dev (HTML, Non-Agentic)
  • Game Dev (Three.js, Agentic)
  • Game Dev (Godot, Agentic)
  • React Native
  • Android (Kotlin)
  • 3D Design (HTML, Non-Agentic)
  • Blender
  • SVG
  • ASCII Art
  • Code Art
  • Code to Video

Office Leaderboards

  • LifeArena
  • Python-PPTX Slides
  • HTML Slides
  • Proprietary Harness Slides
  • Spreadsheet
  • PDF

Image Leaderboards

  • Image
  • Image Editing
  • Single Image Editing
  • Reference to Image

Video Leaderboards

  • Video
  • Image to Video
  • Multi-Image to Video
  • Multimodal to Video
  • Video Editing

Audio Leaderboards

  • Text-to-Speech
  • Audio Realism Bench
  • Speech-to-Speech

Company

  • Methodology
  • Blog
  • Careers
  • Changelog
  • Contact

Resources

  • All Models
  • System Prompts
  • Security
  • Privacy Policy
  • Terms of Use
Drop to attach to your message
Code
Office
Image
Video
Audio
Code
Office
Image
Video
Audio
DesignArena by Intelligence

Overall Preference vs Speed

Generation Time (slower →)Elo Rating (better →)

Overall Preference vs Price

Price per 1M Tokens (Log scale)Elo Rating (better →)

Game Dev

Playable browser games from a single prompt.

Game DevHTMLNon-Agentic
DesignArena by Intelligence
Claude
Fable 5.2
1540

Claude Fable 5.2

GPT-6.2
Astra
1498

GPT-6.2 Astra

GPT-6
Astra (max)
1458

GPT-6 Astra

(max)

Claude
Opus 5.5
1436

Claude Opus 5.5

GPT-6.2
Sol
1431

GPT-6.2 Sol

Claude
Sonnet 5.5
1423

Claude Sonnet 5.5

Inkling
2 Small
1413

Inkling 2 Small

Gemini
4 Carbon
1410

Gemini 4 Carbon

Qwen4-Max
1397

Qwen4-Max

Muse
Wonder (max)
1395

Muse Wonder

(max)

Gemini
4 Neon
1392

Gemini 4 Neon

Kimi
K3.1 Pro
1386

Kimi K3.1 Pro

#180
Llama
4 Scout
746

Llama 4 Scout

Evaluates model ability to generate playable browser games as single-file HTML from real-world user prompts. Real-world users interact with the outputs and select their preferred result.

Game Dev Preference vs Speed

HTMLNon-Agentic
Fast Generation, High Elo
Generation Time (slower →)Elo Rating (better →)10s1.7m16.7m66711491619Claude Fable 5.2GPT-6.2 AstraGPT-6.2 SolGemini 4 CarbonGPT-6.1 SolGemini 4 ArgonGemini 4 HydrogenMuse EmberGemini 2.5 Flash Lite Preview 09-2025Gemini 3.1 Flash-Lite Preview

Game Dev Preference vs Price

HTMLNon-Agentic
Low Cost, High Elo
Average Cost per Generation, measured (Log scale)Elo Rating (better →)$0.003$0.005$0.01$0.03$0.05$0.10$0.25$0.50$1$2.5$588612591600Claude Fable 5.2GPT-6.2 AstraClaude Opus 5.5GPT-6.2 SolInkling 2 SmallGPT-6.1 TerraClaude Haiku 5.5MiMo-V2.6-ProMiMo-V2.5-ProGPT-6 LunaHy4 FlashMercury 2
Models
Claude Fable 5.2
Claude Fable 5.2
GPT-6.2 Astra
GPT-6.2 Astra
Claude Opus 5.5
Claude Opus 5.5
GPT-6.2 Sol
GPT-6.2 Sol
Inkling 2 Small
Inkling 2 Small
GPT-6.1 Terra
GPT-6.1 Terra
Claude Haiku 5.5
Claude Haiku 5.5
MiMo-V2.6-Pro
MiMo-V2.6-Pro
MiMo-V2.5-Pro
MiMo-V2.5-Pro
GPT-6 Luna
GPT-6 Luna
Hy4 Flash
Hy4 Flash
Mercury 2
Mercury 2
GPT-6 Astra (max)
GPT-6 Astra (max)
GPT-6 Astra (xhigh)
GPT-6 Astra (xhigh)
Claude Sonnet 5.5
Claude Sonnet 5.5
Gemini 4 Carbon
Gemini 4 Carbon
Qwen4-Max
Qwen4-Max
Muse Wonder (max)
Muse Wonder (max)
Gemini 4 Neon
Gemini 4 Neon
Kimi K3.1 Pro
Kimi K3.1 Pro
GPT-6.1 Sol
GPT-6.1 Sol
GPT-5.6 Sol (xhigh)
GPT-5.6 Sol (xhigh)
Claude Fable 5.1
Claude Fable 5.1
Gemini 4 Argon
Gemini 4 Argon
Kimi K3
Kimi K3
Gemini 4 Hydrogen
Gemini 4 Hydrogen
Muse Spark 1.3 Max
Muse Spark 1.3 Max
Claude Opus 5
Claude Opus 5
Muse Spark 1.3 (xhigh)
Muse Spark 1.3 (xhigh)
Claude Fable 5
Claude Fable 5
DeepSeek-V4.1-Flash
DeepSeek-V4.1-Flash
GPT-5.6 Sol (Medium)
GPT-5.6 Sol (Medium)
Qwen3.8 Max
Qwen3.8 Max
Gemini 3.7 Flash
Gemini 3.7 Flash
MiniMax M3.1 Flash
MiniMax M3.1 Flash
Ling-3.1-flash
Ling-3.1-flash
Grok 4.7
Grok 4.7
GPT-6 Sol
GPT-6 Sol
Gemini 3.8 Flash
Gemini 3.8 Flash
Muse Spark 1.2
Muse Spark 1.2
GLM-5.3
GLM-5.3
GPT-5.5
GPT-5.5
Grok 4.6
Grok 4.6
Claude Sonnet 5
Claude Sonnet 5
GLM-5.3-Flash
GLM-5.3-Flash
Hy4
Hy4
Muse Spark Open (xhigh)
Muse Spark Open (xhigh)
Muse Spark 1.1
Muse Spark 1.1
DeepSeek-V4.1-Flash (1017)
DeepSeek-V4.1-Flash (1017)
GLM 5.1
GLM 5.1
GLM 5.2
GLM 5.2
Qwen3.7 Max
Qwen3.7 Max
Gemini 3.6 Flash
Gemini 3.6 Flash
Gemini 3.5 Flash
Gemini 3.5 Flash
Grok 4.5
Grok 4.5
Deca 2.6 Ultra
Deca 2.6 Ultra
Claude Opus 4.8
Claude Opus 4.8
Deca 2.5 Ultra
Deca 2.5 Ultra
Qwen3.7 Plus
Qwen3.7 Plus
Deca 2.5 Mini
Deca 2.5 Mini
MiMo-V2.5
MiMo-V2.5
Deca 2.6 Pro
Deca 2.6 Pro
Kimi K2.6
Kimi K2.6
GLM 5 Turbo
GLM 5 Turbo
Hy4 (Direct)
Hy4 (Direct)
DeepSeek-V4-Pro
DeepSeek-V4-Pro
GPT-5.6 Terra
GPT-5.6 Terra
Nex N2 Pro
Nex N2 Pro
Kimi K2.7 Code
Kimi K2.7 Code
Mistral Large 4 Preview
Mistral Large 4 Preview
Hy4 Flash (Direct)
Hy4 Flash (Direct)
GLM 5V Turbo
GLM 5V Turbo
Mercury 3
Mercury 3
Qwen3.6 Plus
Qwen3.6 Plus
MiniMax M2.7
MiniMax M2.7
MiniMax M3
MiniMax M3
DeepSeek-V4-Flash-0731
DeepSeek-V4-Flash-0731
Hy3
Hy3
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
GPT-5.6 Luna
GPT-5.6 Luna
Beam 1.0 (max)
Beam 1.0 (max)
Grok 4.20 Beta (Reasoning)
Grok 4.20 Beta (Reasoning)
Solar Pro 4
Solar Pro 4
Grok 4.20 Beta
Grok 4.20 Beta
Grok 4.3
Grok 4.3
Deca 2.6 Mini
Deca 2.6 Mini
Inkling
Inkling
Step 3.7 Flash
Step 3.7 Flash
Nemotron 3 Ultra
Nemotron 3 Ultra
Muse Glimmer 30B (xhigh)
Muse Glimmer 30B (xhigh)
Solar Mini 4
Solar Mini 4
Nemotron 3.5 Super VL
Nemotron 3.5 Super VL

The Leaderboard

DesignArena by Intelligence
#1
Anthropic logo
?
Claude Fable 5.2
1540
357W / 92L
79.5%
±3.7%
449
Anthropic
797.9s
#2
OpenAI logo
?
GPT-6.2 Astra
1498
423W / 141L
75.0%
±3.6%
564
OpenAI
407.1s
#3
OpenAI logo
?
GPT-6 Astra (max)
1458
872W / 348L
71.5%
±2.5%
1,220
OpenAI
1169.7s
#4
Anthropic logo
?
Claude Opus 5.5
1436
1633W / 824L
66.5%
±1.9%
2,457
Anthropic
428.5s
#5
OpenAI logo
?
GPT-6.2 Sol
1431
405W / 183L
68.9%
±3.7%
588
OpenAI
279.6s
#6
Anthropic logo
?
Claude Sonnet 5.5
1423
1496W / 815L
64.7%
±1.9%
2,311
Anthropic
411.2s
#7
Thinking Machines logo
?
Inkling 2 Small
1413
1522W / 806L
65.4%
±1.9%
2,328
Thinking Machines
704.0s
#8
Google logo
?
Gemini 4 Carbon
1410
467W / 223L
67.7%
±3.5%
690
Google
227.3s
#9
Alibaba logo
?
Qwen4-Max
1397
103W / 63L
62.0%
±7.4%
166
Alibaba
1192.3s
#10
Meta logo
?
Muse Wonder (max)
1395
1609W / 1013L
61.4%
±1.9%
2,622
Meta
233.2s
#11
Google logo
?
Gemini 4 Neon
1392
394W / 217L
64.5%
±3.8%
611
Google
270.0s
#12
Moonshot AI logo
?
Kimi K3.1 Pro
1386
1374W / 763L
64.3%
±2.0%
2,137
Moonshot AI
995.7s
#13
OpenAI logo
?
GPT-6.1 Sol
1383
1933W / 1391L
58.1%
±1.7%
3,324
OpenAI
216.5s
#14
OpenAI logo
?
GPT-5.6 Sol (xhigh)
1351
1648W / 1025L
61.6%
±1.8%
2,673
OpenAI
338.6s
#15
Anthropic logo
?
Claude Fable 5.1
1349
1064W / 723L
59.5%
±2.3%
1,787
Anthropic
412.8s

Updated Nov 21, 2026, 6:33 AM UTC. Elo Rating: A skill-based rating system starting at 1200. Ratings are calculated using the standard Bradley-Terry model. See more in our Methodology page. Margin of Error: Shows ±standard error from the Bradley-Terry model for Elo rating confidence intervals.