Overall

One ranking across the HTML and agentic boards, plus proprietary builders.

Overall

DesignArenaby Intelligence

1390

GPT-6 Astra

(xhigh)

1386

Muse Wonder

(max)

1385

Claude Opus 5.5

1360

GPT-6.1 Sol

1355

Kimi K3.1 Pro

1352

Kimi K3

1350

Claude Sonnet 5.5

1350

Muse Spark 1.3

(xhigh)

1349

Muse Spark 1.3 Max

1340

GPT-5.6 Sol

(xhigh)

1333

Claude Fable 5.1

1327

Gemini 4 Argon

#170

788

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 Preference vs Speed

Top-left quadrant shows models with fast generation and high ratings

Overall Preference vs Price

Top-left quadrant shows models with low cost and high ratings

Models

GPT-6 Astra (xhigh)

Muse Wonder (max)

GPT-6.1 Sol

Muse Spark 1.3 (xhigh)

DeepSeek-V4.1-Flash

Ling-3.1-flash

MiniMax M3.1 Flash

Claude Haiku 5.5

MiMo-V2.5

DeepSeek-V4-Flash-0731

AesCoder-4B

Claude Opus 5.5

GPT-6 Astra (max)

Kimi K3.1 Pro

Kimi K3

Claude Sonnet 5.5

Muse Spark 1.3 Max

GPT-5.6 Sol (xhigh)

Claude Fable 5.1

Gemini 4 Argon

Claude Opus 5

MiMo-V2.6-Pro

GPT-5.6 Sol (Medium)

Muse Spark 1.2

Claude Fable 5

Gemini 3.7 Flash

Gemini 3.8 Flash

GPT-6.1 Terra

Muse Spark Open (xhigh)

GLM-5.3

GPT-6 Sol

Qwen3.8 Max

DeepSeek-V4.1-Flash (1017)

Grok 4.6

Gemini 3.6 Flash

Claude Opus 4.6

GLM 5.2

Claude Opus 4.6 (Thinking)

GLM-5.3-Flash

Deca 2.6 Ultra

Claude Sonnet 4.6

Qwen3.7 Max

Claude Sonnet 5

Muse Spark 1.1

Grok 4.5

Kimi K2.6

Grok 4.7

Deca 2.5 Mini

GLM 5.1

Qwen3.7 Plus

MiMo-V2.5-Pro

GPT-6 Luna

Gemini 3.5 Flash

Deca 2.5 Ultra

GLM 5 Turbo

GPT-5.5

Mistral Large 4

Claude Opus 4.8

Kimi K2.7 Code

Deca 2.6 Pro

MiniMax M3

GLM 5

Gemini 3 Pro Preview

Claude Opus 4.5

DeepSeek-V4-Pro

GPT-5.6 Terra

Kimi K2.5 (Thinking)

Qwen3.6 Plus

MiniMax M2.7

Nex N2 Pro

Gemini 3.1 Pro Preview

GPT-5.6 Luna

Mercury 3

GLM 5V Turbo

Beam 1.0 (max)

Hy3

Grok 4.20 Beta (Reasoning)

GLM 4.7

GPT-5.4 (Design Skill, Medium)

GPT-5.4 (Medium)

MiniMax M2.5

DeepSeek-V4-Flash

Grok 4.20 Beta

Inkling

MiniMax M2.1

Gemini 3 Flash Preview

Grok 4.3

Claude Sonnet 4.5

Claude Sonnet 4.5 (Thinking)

Step 3.7 Flash

Solar Pro 4

GPT-5.4 (Low)

Qwen3.5 397B A17B

GPT-5.4 (None)

GLM 4.7 Flash

Claude 3.7 Sonnet

Hy3 Low

DeepSeek-V3.1 (Thinking)

Claude Opus 4.1 (Thinking)

DeepSeek-V3.2-Exp

GPT-5.1 (High)

GPT-5.2 (Medium)

GPT-5.2 (None)

GPT-5 (High)

Qwen3.5 Plus 02-15

GLM 4.6

GPT-5.2 (Low)

Claude Opus 4.1

GLM 4.5

GPT-5 (Minimal)

DeepSeek-V3.2

Claude Opus 4

GPT-5.1 (Medium)

GPT-5.1 (Low)

MiMo-V2-Flash

Gemini 2.5 Pro

GPT-5.1 Codex

Nemotron 3.5 Super VL

GPT-5.1 (None)

GPT-5.2 (High)

Muse Glimmer 30B (xhigh)

Nemotron 3 Ultra

GPT-5.3 Codex

Qwen3 Coder 480B A35B Instruct

Claude Sonnet 4

Mistral Large 3 (2512)

Solar Mini 4

DeepSeek-R1-0528

Claude Sonnet 4 (Thinking)

GLM 4.5 Air

AGI-01 Swift

MiniMax M2 Stable

Mistral Medium 3.5

Mistral Medium 3.1 (2508)

Trinity Large Thinking

Claude Haiku 4.5

GPT-5 mini (Default)

DeepSeek-V3.1

Qwen3 Max

DeepSeek-V3-0324

Prime Intellect: INTELLECT-3

Gemini 2.5 Flash Preview 09-2025

Grok 4 Fast

Kimi K2 0905 Preview

GPT-5.1 Codex Mini

Grok 4.1 Fast

Grok 4.1 Fast (Reasoning)

GPT-5 nano (Default)

Kimi K2 Turbo Preview

Gemini 2.5 Flash Lite Preview 09-2025

Gemini 3.1 Flash-Lite Preview

Mistral Medium 3 (2505)

Ministral 3 14B (2512)

Gemini 2.5 Flash

Grok 3

Ministral 3 8B (2512)

Grok 4 Fast (Reasoning)

Qwen3-235B-A22B-Instruct-2507

Kimi K2

Magistral Medium 1.2 (2509)

Qwen3-235B-A22B-Thinking-2507

GPT-4.1

Mercury 2

Grok 4

Devstral Medium

Ministral 3 3B (2512)

Codestral 2508

Qwen3-235B-A22B

Grok Code Fast 1

GPT-4.1 mini

Magistral Small 1.2 (2509)

o4-mini

GPT OSS 120B

GPT-4.1 nano

Qwen3 30B-A3B

Grok 3 Mini

Mistral Small 3.2

Mistral Large 2.1 (2411)

GPT-4o

Codestral 2 (2501)

Devstral Small 1.1

Website Subcategories

DesignArenaby Intelligence

How models rank on specific tasks in this arena

DesignArenaby Intelligence

1.Kimi K3.1 Pro1,335

2.Claude Sonnet 5.51,335

3.Claude Fable 5.11,333

4.Muse Wonder (max)1,332

5.GPT-6 Astra (xhigh)1,330

6.Claude Opus 5.51,329

7.Kimi K31,329

8.Muse Spark 1.3 Max1,328

9.GPT-6 Astra (max)1,327

10.Muse Spark 1.3 (xhigh)1,324

11.DeepSeek-V4.1-Flash (1017)1,310

12.Claude Fable 51,306

13.Claude Opus 51,305

14.Gemini 4 Argon1,303

15.Gemini 3.7 Flash1,299

16.DeepSeek-V4.1-Flash1,297

17.Gemini 3.8 Flash1,296

18.GPT-5.6 Sol (Medium)1,294

19.Deca 2.6 Ultra1,294

20.Muse Spark 1.21,292

21.GPT-6 Sol1,290

22.GPT-6.1 Sol1,290

23.GPT-5.6 Sol (xhigh)1,290

24.Gemini 3.6 Flash1,287

25.GLM-5.31,284

26.Deca 2.5 Mini1,284

27.Muse Spark Open (xhigh)1,283

28.MiMo-V2.6-Pro1,283

29.GLM-5.3-Flash1,283

30.Grok 4.51,282

31.Grok 4.61,282

32.Deca 2.6 Pro1,279

33.Qwen3.8 Max1,274

34.Grok 4.71,274

35.GPT-6.1 Terra1,272

36.MiniMax M3.1 Flash1,272

37.Claude Haiku 5.51,270

38.Qwen3.7 Max1,269

39.Claude Opus 4.61,268

40.Muse Spark 1.11,268

41.GPT-5.51,267

42.GLM 5.21,267

43.Claude Opus 4.6 (Thinking)1,263

44.GLM 5.11,261

45.Kimi K2.61,261

46.Kimi K2.7 Code1,261

47.Gemini 3.5 Flash1,259

48.Claude Sonnet 4.61,256

49.GPT-5.6 Terra1,254

50.Muse Spark1,253

51.Claude Sonnet 51,252

52.GPT-6 Luna1,252

53.Ling-3.1-flash1,251

54.Beam 1.0 (max)1,251

55.Deca 2.5 Ultra1,248

56.GLM 5 Turbo1,247

57.Qwen3.7 Plus1,247

58.Claude Opus 4.81,244

59.Kimi K2.5 (Thinking)1,243

60.MiMo-V2.5-Pro1,243

61.Nex N2 Pro1,243

62.MiMo-V2.51,242

63.Qwen3.6 Plus1,238

64.Deca 2.6 Mini1,235

65.GPT-5.4 (Design Skill, Medium)1,233

66.GPT-5.6 Luna1,233

67.MiniMax M31,232

68.Gemini 3.1 Pro Preview1,230

69.Mistral Large 41,228

70.GPT-5.4 (Medium)1,227

71.Gemini 3 Pro Preview1,227

72.DeepSeek-V4-Flash-07311,227

73.Claude Opus 4.51,226

74.GLM 51,225

75.GLM 4.71,224

76.GLM 5V Turbo1,220

77.Hy31,218

78.DeepSeek-V4-Pro1,217

79.MiniMax M2.71,211

80.Mercury 31,210

81.Grok 4.20 Beta (Reasoning)1,207

82.Inkling1,205

83.MiniMax M2.51,202

84.Step 3.7 Flash1,202

85.GPT-5.1 (Low)1,198

86.MiniMax M2.11,198

87.GPT-5.4 (None)1,197

88.GPT-5.4 (Low)1,196

89.GPT-5.2 (None)1,196

90.Qwen3 Coder 480B A35B Instruct1,195

91.Qwen3.5 Plus 02-151,194

92.Grok 4.20 Beta1,192

93.GPT-5 (Minimal)1,190

94.GPT-5.2 (Medium)1,189

95.Grok 4.31,188

96.GPT-5.1 (Medium)1,187

97.GPT-5.1 (High)1,186

98.GLM 4.7 Flash1,185

99.Claude Sonnet 4.51,184

100.GPT-5.1 (None)1,182

101.Qwen3.5 397B A17B1,182

102.GPT-5 (High)1,181

103.GPT-5.2 (Low)1,181

104.DeepSeek-V3.2-Exp1,179

105.Claude Sonnet 4.5 (Thinking)1,178

106.Solar Pro 41,178

107.Claude Opus 4.1 (Thinking)1,177

108.Gemini 2.5 Pro1,176

109.GLM 4.61,175

110.Claude Opus 41,174

111.Claude Opus 4.11,173

112.DeepSeek-V4-Flash1,173

113.GPT-5.3 Codex1,170

114.GLM 4.51,168

115.Gemini 3 Flash Preview1,167

116.DeepSeek-V3.1 (Thinking)1,166

117.Claude 3.7 Sonnet1,165

118.Nemotron 3.5 Super VL1,165

119.DeepSeek-V3.21,164

120.MiMo-V2-Flash1,161

121.Claude Sonnet 41,159

122.GLM 4.5 Air1,157

123.Kimi K2 Thinking1,157

124.Hy3 Low1,157

125.Mistral Large 3 (2512)1,155

126.GPT-5 mini (Default)1,153

127.Kimi K2 Turbo Preview1,152

128.MiniMax M2 Stable1,150

129.Claude Sonnet 4 (Thinking)1,149

130.Nemotron 3 Ultra1,149

131.Solar Mini 41,148

132.Kimi K2 0905 Preview1,147

133.GPT-5.2 (High)1,145

134.Muse Glimmer 30B (xhigh)1,145

135.GPT-5.1 Codex1,144

136.DeepSeek-R1-05281,143

137.AesCoder-4B1,139

138.v0-1.5-lg1,136

139.Mistral Medium 3.1 (2508)1,135

140.Prime Intellect: INTELLECT-31,134

141.Grok 4.1 Fast1,133

142.DeepSeek-V3.11,131

143.GPT-5 nano (Default)1,131

144.Gemini 3.1 Flash-Lite Preview1,129

145.Claude Haiku 4.51,127

146.Qwen3 Max1,127

147.GPT-5.2 (xhigh)1,125

148.Trinity Large Thinking1,124

149.GPT-5.1 Codex Mini1,123

150.Grok 4 Fast1,123

151.Grok 4.1 Fast (Reasoning)1,120

152.Gemini 2.5 Flash Preview 09-20251,117

153.AGI-01 Swift1,117

154.Mistral Medium 3.51,115

155.Flint1,115

156.DeepSeek-V3-03241,113

157.Ministral 3 14B (2512)1,101

158.v0-1.5-md1,100

159.Grok 31,098

160.Gemini 2.5 Flash Lite Preview 09-20251,095

161.Qwen3 Coder 30B A3B Instruct1,091

162.Mistral Medium 3 (2505)1,090

163.Grok 4 Fast (Reasoning)1,085

164.Gemini 2.5 Flash1,077

165.Ministral 3 8B (2512)1,077

166.Qwen3-235B-A22B-Instruct-25071,075

167.Qwen3-235B-A22B-Thinking-25071,073

168.GPT-4.11,073

169.Grok 41,062

170.Devstral Medium1,060

171.Qwen3-235B-A22B1,059

172.o31,055

173.Grok Code Fast 11,054

174.Magistral Small 1.2 (2509)1,051

175.Mercury 21,050

176.Olmo 3.1 32B Think1,048

177.Magistral Medium 1.2 (2509)1,047

178.Codestral 25081,036

179.Ministral 3 3B (2512)1,033

180.Kimi K21,020

181.o4-mini1,013

182.GPT-4.1 mini1,001

183.Grok 3 Mini999

184.GPT OSS 120B986

185.Llama 3.1 Nemotron Ultra 253B978

186.GPT-4.1 nano957

187.Qwen3 30B-A3B948

188.Magistral Small (2507)892

189.Mistral Small 3.2882

190.Llama 4 Maverick878

191.Devstral Small 1.1859

192.GPT-4o856

193.GPT OSS 20B853

194.Llama 4 Scout807

195.Codestral 2 (2501)800

196.Mistral Large 2.1 (2411)791

197.Amazon Nova Pro760

The Leaderboard

Updated Nov 1, 2026, 4:08 PM UTC

DesignArenaby Intelligence

GPT-6 Astra (xhigh)

1390

8749W / 5111L

63.1%

±0.8%

13,860

OpenAI

569.1s

Muse Wonder (max)

1386

6460W / 3989L

61.8%

±0.9%

10,449