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
  • Agentic Image to HTML
  • 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

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

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 →)

Overall

One ranking across the agentic and HTML boards.

Overall HTML
DesignArena by Intelligence
GPT-6
Astra (xhigh)
1392

GPT-6 Astra

(xhigh)

Muse
Wonder (max)
1388

Muse Wonder

(max)

Inkling
2 Small
1382

Inkling 2 Small

Claude
Opus 5.5
1380

Claude Opus 5.5

Claude
Fable 5.2
1370

Claude Fable 5.2

GPT-6.1
Sol
1358

GPT-6.1 Sol

Kimi
K3
1348

Kimi K3

Muse
Spark 1.3 Max
1348

Muse Spark 1.3 Max

Kimi
K3.1 Pro
1344

Kimi K3.1 Pro

Muse
Ember
1343

Muse Ember

Claude
Sonnet 5.5
1340

Claude Sonnet 5.5

Gemini
4 Hydrogen
1339

Gemini 4 Hydrogen

#177
Llama
4 Scout
774

Llama 4 Scout

Evaluates model ability across a composite of Website, UI Component, Game Development, Data Visualization, and 3D tasks, each produced as a single-file HTML output. Results aggregate real-world user preferences across these categories to provide an overall view of coding performance.

Overall HTML Preference vs Speed

Fast Generation, High Elo
Generation Time (slower →)Elo Rating (better →)10s1.7m16.7m71211641454GPT-6 Astra (xhigh)Muse Wonder (max)Muse Spark 1.3 (xhigh)Muse EmberGemini 2.5 Flash Lite Preview 09-2025Gemini 3.1 Flash-Lite Preview

Overall HTML Preference vs Price

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$595112621432GPT-6 Astra (xhigh)Muse Wonder (max)Inkling 2 SmallMiMo-V2.6-ProMiniMax M3.1 FlashClaude Haiku 5.5GPT-6 LunaHy4 FlashMercury 2
Models
GPT-6 Astra (xhigh)
GPT-6 Astra (xhigh)
Muse Wonder (max)
Muse Wonder (max)
Inkling 2 Small
Inkling 2 Small
MiMo-V2.6-Pro
MiMo-V2.6-Pro
MiniMax M3.1 Flash
MiniMax M3.1 Flash
Claude Haiku 5.5
Claude Haiku 5.5
GPT-6 Luna
GPT-6 Luna
Hy4 Flash
Hy4 Flash
Mercury 2
Mercury 2
Claude Opus 5.5
Claude Opus 5.5
GPT-6 Astra (max)
GPT-6 Astra (max)
Claude Fable 5.2
Claude Fable 5.2
GPT-6.1 Sol
GPT-6.1 Sol
Kimi K3
Kimi K3
Muse Spark 1.3 Max
Muse Spark 1.3 Max
Muse Spark 1.3 (xhigh)
Muse Spark 1.3 (xhigh)
Kimi K3.1 Pro
Kimi K3.1 Pro
Claude Sonnet 5.5
Claude Sonnet 5.5
Gemini 4 Hydrogen
Gemini 4 Hydrogen
Gemini 4 Carbon
Gemini 4 Carbon
GPT-5.6 Sol (xhigh)
GPT-5.6 Sol (xhigh)
Claude Fable 5.1
Claude Fable 5.1
Gemini 4 Argon
Gemini 4 Argon
Claude Opus 5
Claude Opus 5
DeepSeek-V4.1-Flash
DeepSeek-V4.1-Flash
GPT-5.6 Sol (Medium)
GPT-5.6 Sol (Medium)
Muse Spark 1.2
Muse Spark 1.2
GPT-6.1 Terra
GPT-6.1 Terra
Ling-3.1-flash
Ling-3.1-flash
Claude Fable 5
Claude Fable 5
Gemini 3.7 Flash
Gemini 3.7 Flash
Muse Spark Open (xhigh)
Muse Spark Open (xhigh)
GPT-6 Sol
GPT-6 Sol
Gemini 3.8 Flash
Gemini 3.8 Flash
Qwen3.8 Max
Qwen3.8 Max
DeepSeek-V4.1-Flash (1017)
DeepSeek-V4.1-Flash (1017)
GLM-5.3
GLM-5.3
Gemini 3.6 Flash
Gemini 3.6 Flash
Grok 4.6
Grok 4.6
GLM 5.2
GLM 5.2
Deca 2.6 Ultra
Deca 2.6 Ultra
Claude Sonnet 5
Claude Sonnet 5
GLM-5.3-Flash
GLM-5.3-Flash
Muse Spark 1.1
Muse Spark 1.1
Qwen3.7 Max
Qwen3.7 Max
Grok 4.5
Grok 4.5
Grok 4.7
Grok 4.7
Deca 2.5 Mini
Deca 2.5 Mini
Kimi K2.6
Kimi K2.6
MiMo-V2.5-Pro
MiMo-V2.5-Pro
GLM 5.1
GLM 5.1
Qwen3.7 Plus
Qwen3.7 Plus
Gemini 3.5 Flash
Gemini 3.5 Flash
Deca 2.5 Ultra
Deca 2.5 Ultra
Hy4
Hy4
Mistral Large 4 Preview
Mistral Large 4 Preview
GLM 5 Turbo
GLM 5 Turbo
MiMo-V2.5
MiMo-V2.5
GPT-5.5
GPT-5.5
Claude Opus 4.8
Claude Opus 4.8
Deca 2.6 Pro
Deca 2.6 Pro
Kimi K2.7 Code
Kimi K2.7 Code
MiniMax M3
MiniMax M3
DeepSeek-V4-Pro
DeepSeek-V4-Pro
GPT-5.6 Terra
GPT-5.6 Terra
Qwen3.6 Plus
Qwen3.6 Plus
Mercury 3
Mercury 3
Beam 1.0 (max)
Beam 1.0 (max)
MiniMax M2.7
MiniMax M2.7
Nex N2 Pro
Nex N2 Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
GPT-5.6 Luna
GPT-5.6 Luna
DeepSeek-V4-Flash-0731
DeepSeek-V4-Flash-0731
GLM 5V Turbo
GLM 5V Turbo
Hy3
Hy3
Grok 4.20 Beta (Reasoning)
Grok 4.20 Beta (Reasoning)
Grok 4.20 Beta
Grok 4.20 Beta
Inkling
Inkling
Grok 4.3
Grok 4.3
Solar Pro 4
Solar Pro 4
Deca 2.6 Mini
Deca 2.6 Mini
Step 3.7 Flash
Step 3.7 Flash
Muse Glimmer 30B (xhigh)
Muse Glimmer 30B (xhigh)
Nemotron 3.5 Super VL
Nemotron 3.5 Super VL
Nemotron 3 Ultra
Nemotron 3 Ultra
Solar Mini 4
Solar Mini 4

Website Subcategories

DesignArena by Intelligence

How models rank on specific tasks in this arena

DesignArena by Intelligence
1.GPT-6.2 Astra1,388
2.Claude Fable 5.21,378
3.GPT-6 Astra (max)1,362
4.Inkling 2 Small1,355
5.GPT-6 Astra (xhigh)1,355
6.Muse Spark 1.3 Max1,352
7.Kimi K3.1 Pro1,349
8.Kimi K31,333
9.Claude Fable 5.11,332
10.Muse Ember1,330
11.Claude Sonnet 5.51,328
12.Muse Spark 1.3 (xhigh)1,328
13.Muse Wonder (max)1,328
14.Claude Opus 5.51,327
15.GPT-6.1 Sol1,319
16.Gemini 4 Hydrogen1,311
17.Gemini 4 Argon1,306
18.Gemini 4 Carbon1,305
19.DeepSeek-V4.1-Flash (1017)1,304
20.Claude Fable 51,303
21.Claude Opus 51,303
22.GPT-5.6 Sol (xhigh)1,299
23.GPT-6 Sol1,298
24.Deca 2.5 Mini1,296
25.Deca 2.6 Ultra1,294
26.DeepSeek-V4.1-Flash1,294
27.MiMo-V2.6-Pro1,291
28.Gemini 3.8 Flash1,291
29.Gemini 3.7 Flash1,290
30.GPT-5.6 Sol (Medium)1,288
31.MiniMax M3.1 Flash1,286
32.GPT-6.1 Terra1,284
33.Muse Spark 1.21,284
34.GLM-5.3-Flash1,280
35.Gemini 3.6 Flash1,277
36.Hy41,277
37.Grok 4.51,275
38.Ling-3.1-flash1,273
39.Grok 4.71,272
40.Muse Spark Open (xhigh)1,270
41.Qwen3.8 Max1,269
42.GLM 5.21,267
43.Muse Spark 1.11,264
44.Grok 4.61,264
45.GLM 5.11,263
46.Claude Haiku 5.51,262
47.Qwen3.7 Max1,262
48.GPT-5.51,260
49.Claude Opus 4.61,258
50.Deca 2.5 Ultra1,256
51.GLM-5.31,255
52.Claude Opus 4.6 (Thinking)1,253
53.Kimi K2.7 Code1,252
54.Kimi K2.61,252
55.Claude Sonnet 51,249
56.GPT-6 Luna1,247
57.Claude Sonnet 4.61,246
58.Gemini 3.5 Flash1,245
59.GPT-5.6 Terra1,242
60.Muse Spark1,242
61.Nex N2 Pro1,239
62.MiMo-V2.5-Pro1,238
63.Qwen3.7 Plus1,238
64.GLM 5 Turbo1,236
65.Kimi K2.5 (Thinking)1,232
66.Claude Opus 4.81,230
67.MiMo-V2.51,230
68.Mistral Large 4 Preview1,227
69.Qwen3.6 Plus1,226
70.GPT-5.4 (Design Skill, Medium)1,222
71.DeepSeek-V4-Flash-07311,221
72.Gemini 3.1 Pro Preview1,219
73.MiniMax M31,217
74.Gemini 3 Pro Preview1,216
75.GPT-5.4 (Medium)1,216
76.GPT-5.6 Luna1,215
77.GLM 51,214
78.Claude Opus 4.51,214
79.GLM 4.71,212
80.Hy31,210
81.GLM 5V Turbo1,209
82.DeepSeek-V4-Pro1,207
83.MiniMax M2.71,199
84.Grok 4.20 Beta (Reasoning)1,197
85.Beam 1.0 (max)1,195
86.Hy4 Flash1,195
87.MiniMax M2.51,191
88.Step 3.7 Flash1,188
89.MiniMax M2.11,187
90.GPT-5.1 (Low)1,187
91.GPT-5.4 (None)1,186
92.GPT-5.2 (None)1,185
93.Inkling1,185
94.Solar Pro 41,185
95.GPT-5.4 (Low)1,185
96.Qwen3 Coder 480B A35B Instruct1,184
97.Qwen3.5 Plus 02-151,183
98.GPT-5 (Minimal)1,179
99.Grok 4.20 Beta1,178
100.GPT-5.2 (Medium)1,177
101.GPT-5.1 (Medium)1,176
102.GPT-5.1 (High)1,175
103.GLM 4.7 Flash1,174
104.Claude Sonnet 4.51,173
105.Qwen3.5 397B A17B1,172
106.Grok 4.31,172
107.GPT-5.1 (None)1,171
108.GPT-5 (High)1,170
109.GPT-5.2 (Low)1,170
110.DeepSeek-V3.2-Exp1,168
111.Claude Sonnet 4.5 (Thinking)1,167
112.Claude Opus 4.1 (Thinking)1,166
113.Gemini 2.5 Pro1,165
114.GLM 4.61,164
115.Deca 2.6 Mini1,163
116.Claude Opus 41,162
117.Claude Opus 4.11,162
118.DeepSeek-V4-Flash1,162
119.GPT-5.3 Codex1,159
120.GLM 4.51,157
121.Gemini 3 Flash Preview1,156
122.Mercury 31,156
123.DeepSeek-V3.1 (Thinking)1,155
124.Claude 3.7 Sonnet1,154
125.DeepSeek-V3.21,153
126.MiMo-V2-Flash1,149
127.Claude Sonnet 41,148
128.GLM 4.5 Air1,146
129.Kimi K2 Thinking1,146
130.Hy3 Low1,145
131.Mistral Large 3 (2512)1,144
132.GPT-5 mini (Default)1,142
133.Kimi K2 Turbo Preview1,141
134.Muse Glimmer 30B (xhigh)1,141
135.MiniMax M2 Stable1,139
136.Claude Sonnet 4 (Thinking)1,138
137.Kimi K2 0905 Preview1,136
138.GPT-5.2 (High)1,134
139.GPT-5.1 Codex1,133
140.DeepSeek-R1-05281,132
141.AesCoder-4B1,128
142.Solar Mini 41,127
143.v0-1.5-lg1,125
144.Mistral Medium 3.1 (2508)1,123
145.Prime Intellect: INTELLECT-31,122
146.Grok 4.1 Fast1,122
147.Nemotron 3 Ultra1,122
148.DeepSeek-V3.11,120
149.GPT-5 nano (Default)1,120
150.Gemini 3.1 Flash-Lite Preview1,117
151.Qwen3 Max1,116
152.Claude Haiku 4.51,116
153.GPT-5.2 (xhigh)1,114
154.Nemotron 3.5 Super VL1,113
155.Trinity Large Thinking1,113
156.Grok 4 Fast1,112
157.GPT-5.1 Codex Mini1,112
158.Grok 4.1 Fast (Reasoning)1,109
159.Gemini 2.5 Flash Preview 09-20251,106
160.AGI-01 Swift1,105
161.Mistral Medium 3.51,104
162.DeepSeek-V3-03241,102
163.v0-1.5-md1,089
164.Ministral 3 14B (2512)1,089
165.Grok 31,087
166.Gemini 2.5 Flash Lite Preview 09-20251,084
167.Qwen3 Coder 30B A3B Instruct1,080
168.Mistral Medium 3 (2505)1,079
169.Grok 4 Fast (Reasoning)1,074
170.Flint1,070
171.Gemini 2.5 Flash1,066
172.Ministral 3 8B (2512)1,066
173.Qwen3-235B-A22B-Instruct-25071,064
174.GPT-4.11,062
175.Qwen3-235B-A22B-Thinking-25071,062
176.Grok 41,051
177.Devstral Medium1,049
178.Qwen3-235B-A22B1,048
179.o31,044
180.Grok Code Fast 11,043
181.Magistral Small 1.2 (2509)1,040
182.Olmo 3.1 32B Think1,037
183.Magistral Medium 1.2 (2509)1,036
184.Codestral 25081,025
185.Ministral 3 3B (2512)1,022
186.Kimi K21,009
187.o4-mini1,001
188.Mercury 2997
189.GPT-4.1 mini990
190.Grok 3 Mini988
191.GPT OSS 120B975
192.Llama 3.1 Nemotron Ultra 253B967
193.GPT-4.1 nano946
194.Qwen3 30B-A3B937
195.Magistral Small (2507)881
196.Mistral Small 3.2871
197.Llama 4 Maverick867
198.Devstral Small 1.1848
199.GPT-4o845
200.GPT OSS 20B842
201.Llama 4 Scout796
202.Codestral 2 (2501)789
203.Mistral Large 2.1 (2411)780
204.Amazon Nova Pro749

General Purpose ranks models on prompts that don’t fit any other category here, like open-ended, one-line or mixed requests.

The Leaderboard

Updated Nov 18, 2026, 5:58 PM UTC

DesignArena by Intelligence
#1
OpenAI logo
?
GPT-6 Astra (xhigh)
1392
8597W / 4814L
64.1%
±0.8%
13,411
OpenAI
577.5s
#2
Meta logo
?
Muse Wonder (max)
1388
6362W / 3813L
62.5%
±0.9%
10,175
Meta
195.2s
#3
Thinking Machines logo
?
Inkling 2 Small
1382
3493W / 2039L
63.1%
±1.3%
5,532
Thinking Machines
639.5s
#4
Anthropic logo
?
Claude Opus 5.5
1380
6318W / 4056L
60.9%
±0.9%
10,374
Anthropic
369.8s
#5
Anthropic logo
?
Claude Fable 5.2
1370
1596W / 965L
62.3%
±1.9%
2,561
Anthropic
711.9s
#6
OpenAI logo
?
GPT-6.1 Sol
1358
5653W / 4269L
57.0%
±1.0%
9,922
OpenAI
219.1s
#7
Moonshot AI logo
?
Kimi K3
1348
6877W / 4509L
60.4%
±0.9%
11,386
Moonshot AI
788.4s
#8
Meta logo
?
Muse Spark 1.3 Max
1348
20287W / 14695L
58.0%
±0.5%
34,982
Meta
267.1s
#9
Moonshot AI logo
?
Kimi K3.1 Pro
1344
3912W / 2568L
60.4%
±1.2%
6,480
Moonshot AI
1083.3s
#10
Meta logo
?
Muse Ember
1343
2542W / 1645L
60.7%
±1.5%
4,187
Meta
32.7s
#11
Anthropic logo
?
Claude Sonnet 5.5
1340
4297W / 3423L
55.7%
±1.1%
7,720
Anthropic
409.9s
#12
Google logo
?
Gemini 4 Hydrogen
1339
1754W / 1273L
58.0%
±1.8%
3,027
Google
102.2s
#13
Google logo
?
Gemini 4 Carbon
1337
2031W / 1421L
58.8%
±1.6%
3,452
Google
233.2s
#14
OpenAI logo
?
GPT-5.6 Sol (xhigh)
1333
7999W / 5635L
58.7%
±0.8%
13,634
OpenAI
283.4s
#15
Anthropic logo
?
Claude Fable 5.1
1326
5385W / 3979L
57.5%
±1.0%
9,364
Anthropic
334.3s

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.