Benchmark Almanac

DesignArena Website

Muse Wonder 1,380 leads since October 2026
Muse Wonder 1,380 leads since October 2026
In use

Models build a complete website as one HTML file from a real user prompt. Users compare the rendered pages and vote for the better one.

Filters split it by site type, such as e-commerce, portfolio, dashboard and blog. DesignArena blog posts also call it the Web Design (Non-Agentic) arena. One of 40 DesignArena boards. DesignArena ranks entries with Bradley-Terry ratings from user votes.

Kind
Web and app front ends
Level
Everyday
Scored
Ranked by votes
Answers
Open-ended
Tasks
All public
Strongest model tested
Claude Fable 5.2 #1 on the capability index
Last in a launch post
November 2026
Last model added
November 2026
Scores refreshed
November 12th, 2026
182
Entries on its own leaderboard, 151 models we track
2
Launch posts list it, from 1 lab

Muse Wonder leads with 1,380

Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.

Muse Wonder leads with 1,380, claims included

Best score per model from every source, including labs’ own numbers and claims Epoch AI collected from reports and papers. Labs pick their own settings, so a claim can beat an independent run of the same model.

182 entries. Scroll sideways for the rest. Bars start at 600.

  1. 1,380 Muse Wonder
  2. 1,361 Muse Spark 1.3
  3. 1,352 Claude Fable 5.2
  4. 1,341 GPT-6 Astra
  5. 1,337 Kimi K3
  6. 1,332 Inkling 2 Small
  7. 1,331 Muse Ember
  8. 1,325 Claude Opus 5.5
  9. 1,323 Kimi K3.1 Pro
  10. 1,320 GPT-5.6 Sol
  11. 1,317 Gemini 4 Argon
  12. 1,315 GPT-6.1 Sol
  13. 1,312 MiMo-V2.6 Pro
  14. 1,311 Muse Spark 1.2
  15. 1,311 Claude Sonnet 5.5
  16. 1,308 Muse Spark Open
  17. 1,306 Claude Fable 5.1
  18. 1,305 Claude Opus 5
  19. 1,299 DeepSeek V4.1 Flash
  20. 1,296 Gemini 3.7 Flash
  21. 1,293 Gemini 3.6 Flash
  22. 1,293 Ling-3.1-flash
  23. 1,293 Gemini 4 Carbon
  24. 1,292 Gemini 3.8 Flash
  25. 1,290 GPT-6 Sol
  26. 1,289 Claude Fable 5
  27. 1,287 GPT-6.1 Terra
  28. 1,284 Claude Opus 4.6
  29. 1,280 GLM-5.3
  30. 1,278 Deca 2.5 Mini
  31. 1,278 Claude Sonnet 4.6
  32. 1,278 GLM-5.2
  33. 1,278 Grok 4.6
  34. 1,278 MiniMax-M3.1-Flash
  35. 1,274 Grok 4.5
  36. 1,273 Deca 2.6 Ultra
  37. 1,270 Qwen 3.8 Max
  38. 1,269 Claude Sonnet 5
  39. 1,269 GPT-6 Luna
  40. 1,268 Qwen3.7-Max
  41. 1,266 Deca 2.5 Ultra
  42. 1,264 Kimi K2.6
  43. 1,264 MiMo-V2.5-Pro
  44. 1,264 Muse Spark 1.1
  45. 1,263 GLM-5.1
  46. 1,262 Qwen3.7-Plus
  47. 1,261 MiMo-V2.5
  48. 1,261 Gemini 3.5 Flash
  49. 1,261 GPT-5.6 Terra
  50. 1,259 Kimi K2.7 Code
  51. 1,259 Mistral Large 4
  52. 1,258 GLM-5.3-Flash
  53. 1,255 GLM-5-Turbo
  54. 1,254 Muse Spark
  55. 1,254 Claude Haiku 5.5
  56. 1,253 Tencent Hy4
  57. 1,251 Claude Opus 4.8
  58. 1,249 GPT-5.5
  59. 1,249 MiniMax-M3
  60. 1,248 GPT-5.6 Luna
  61. 1,246 Gemini 3 Pro
  62. 1,245 Grok 4.7
  63. 1,245 Beam 1.0
  64. 1,242 Kimi K2.5
  65. 1,241 GLM-5
  66. 1,240 Claude Opus 4.5
  67. 1,235 MiniMax-M2.7
  68. 1,235 Qwen 3.6 Plus
  69. 1,234 Deca 2.6 Pro
  70. 1,231 DeepSeek V4 Flash 0731
  71. 1,231 Mercury 3
  72. 1,228 DeepSeek-V4-Pro
  73. 1,227 Gemini 3.1 Pro
  74. 1,224 GLM-5V-Turbo
  75. 1,222 Grok 4.20 Beta
  76. 1,222 Tencent Hy3
  77. 1,219 GLM-4.7
  78. 1,216 Inkling
  79. 1,215 Nex N2 Pro
  80. 1,215 MiniMax-M2.5
  81. 1,213 GPT-5.4 (Design Skill, Medium)
  82. 1,208 GPT-5.4
  83. 1,200 DeepSeek-V4-Flash
  84. 1,194 MiniMax-M2.1
  85. 1,192 Deca 2.6 Mini
  86. 1,189 Gemini 3 Flash
  87. 1,188 GPT-5.2
  88. 1,187 glm-4.7-flash
  89. 1,187 Grok 4.3
  90. 1,187 Step 3.7 Flash
  91. 1,186 Muse Glimmer 30B
  92. 1,186 Claude 3.7 Sonnet
  93. 1,184 Qwen3.5 397B-A17B
  94. 1,183 Claude Sonnet 4.5
  95. 1,181 Qwen3.5 Plus 02-15
  96. 1,180 DeepSeek-V3.1
  97. 1,180 GPT-5.1
  98. 1,177 GPT-5
  99. 1,172 DeepSeek-V3.2-Exp
  100. 1,170 Claude Opus 4.1
  101. 1,168 DeepSeek-V3.2
  102. 1,167 GLM-4.6
  103. 1,164 Solar Pro 4
  104. 1,163 GLM-4.5
  105. 1,160 Gemini 2.5 Pro
  106. 1,160 MiMo-V2-Flash
  107. 1,160 Nemotron 3.5 Super VL
  108. 1,158 Claude Opus 4
  109. 1,156 Flint
  110. 1,156 GPT-5.3 Codex
  111. 1,155 GPT-5.1-Codex
  112. 1,155 Mistral Large 3
  113. 1,152 Qwen3 Coder 480B A35B Instruct
  114. 1,142 DeepSeek-R1
  115. 1,141 Solar Mini 4
  116. 1,139 v0-1.5-lg
  117. 1,139 Claude Sonnet 4
  118. 1,139 GLM-4.5-Air
  119. 1,136 MiniMax M2 Stable
  120. 1,135 Mistral Medium 3.5
  121. 1,134 AesCoder-4B
  122. 1,131 Nemotron 3 Ultra
  123. 1,130 Trinity Large Thinking
  124. 1,126 Mistral Medium 3.1
  125. 1,118 GPT-5 mini (Default)
  126. 1,115 Claude Haiku 4.5
  127. 1,113 DeepSeek-V3
  128. 1,112 Qwen3-Max
  129. 1,110 Prime Intellect: INTELLECT-3
  130. 1,108 Gemini 2.5 Flash
  131. 1,107 Grok 4 Fast
  132. 1,106 Kimi K2 Thinking
  133. 1,104 GPT-5.1-Codex-mini
  134. 1,100 AGI-01 Swift
  135. 1,100 Kimi K2 0905 Preview
  136. 1,098 Grok 4.1 Fast
  137. 1,094 GPT-5 nano (Default)
  138. 1,092 Gemini 2.5 Flash-Lite
  139. 1,082 Kimi K2 Turbo Preview
  140. 1,082 Kimi K2
  141. 1,080 Qwen3-Coder-30B-A3B-Instruct
  142. 1,076 Gemini 3.1 Flash-Lite
  143. 1,074 Ministral 3 14B
  144. 1,072 Mistral Medium 3 (2505)
  145. 1,058 Ministral 3 8B Instruct
  146. 1,053 v0-1.5-md
  147. 1,052 Grok 3
  148. 1,051 Qwen3-235B-A22B-Instruct-2507
  149. 1,046 Qwen3-235B-A22B-Thinking
  150. 1,033 Magistral Medium 1.2 (2509)
  151. 1,032 GPT-4.1
  152. 1,029 o3
  153. 1,023 Qwen3-235B-A22B
  154. 1,021 Ministral 3 3B Instruct
  155. 1,012 Devstral Medium
  156. 1,011 Mercury 2
  157. 1,007 Grok 4
  158. 1,006 Codestral 2508
  159. 990 GPT-4.1 mini
  160. 989 grok-code-fast-1
  161. 985 Magistral Small 1.2 (2509)
  162. 978 o4-mini
  163. 971 Olmo 3.1 32B Think
  164. 966 GPT-4.1 nano
  165. 961 gpt-oss-120b
  166. 948 Qwen3-30B-A3B
  167. 928 Llama 3.1 Nemotron Ultra 253B
  168. 923 Qwen3 30B-A3B Thinking 2507
  169. 922 Grok-3 mini
  170. 905 Magistral Small 1.1
  171. 889 Mistral Small 3.2
  172. 864 Llama 4 Maverick
  173. 851 Mistral Large 2.1 (2411)
  174. 850 Grok-2
  175. 845 gpt-oss-20b
  176. 828 Amazon Nova Premier
  177. 824 GPT-4o
  178. 802 Codestral 2 (2501)
  179. 795 Devstral Small 1.1
  180. 789 Amazon Nova Pro
  181. 777 Gemini 1.5 Pro
  182. 743 Llama 4 Scout

Bars start at 600.

  1. 1 Muse Wonder max 1,380
  2. 2 Muse Spark 1.3 xhigh 1,361
  3. 3 Claude Fable 5.2 1,352
  4. 4 GPT-6 Astra xhigh 1,341
  5. 5 Kimi K3 1,337
  6. 6 Inkling 2 Small 1,332
  7. 7 Muse Ember 1,331
  8. 8 Claude Opus 5.5 1,325
  9. 9 Kimi K3.1 Pro 1,323
  10. 10 GPT-5.6 Sol medium, xhigh 1,320
  11. 11 Gemini 4 Argon 1,317
  12. 12 GPT-6.1 Sol 1,315
  13. 13 MiMo-V2.6 Pro 1,312
  14. 14 Muse Spark 1.2 1,311
  15. 15 Claude Sonnet 5.5 1,311
  16. 16 Muse Spark Open xhigh 1,308
  17. 17 Claude Fable 5.1 1,306
  18. 18 Claude Opus 5 1,305
  19. 19 DeepSeek V4.1 Flash 1,299
  20. 20 Gemini 3.7 Flash 1,296
  21. 21 Gemini 3.6 Flash 1,293
  22. 22 Ling-3.1-flash 1,293
  23. 23 Gemini 4 Carbon 1,293
  24. 24 Gemini 3.8 Flash 1,292
  25. 25 GPT-6 Sol 1,290
  26. 26 Claude Fable 5 1,289
  27. 27 GPT-6.1 Terra 1,287
  28. 28 Claude Opus 4.6 1,284
  29. 29 GLM-5.3 1,280
  30. 30 Deca 2.5 Mini 1,278
  31. 31 Claude Sonnet 4.6 1,278
  32. 32 GLM-5.2 1,278
  33. 33 Grok 4.6 1,278
  34. 34 MiniMax-M3.1-Flash 1,278
  35. 35 Grok 4.5 1,274
  36. 36 Deca 2.6 Ultra 1,273
  37. 37 Qwen 3.8 Max 1,270
  38. 38 Claude Sonnet 5 1,269
  39. 39 GPT-6 Luna 1,269
  40. 40 Qwen3.7-Max 1,268
  41. 41 Deca 2.5 Ultra 2 1,266
  42. 42 Kimi K2.6 1,264
  43. 43 MiMo-V2.5-Pro 1,264
  44. 44 Muse Spark 1.1 1,264
  45. 45 GLM-5.1 1,263
  46. 46 Qwen3.7-Plus 1,262
  47. 47 MiMo-V2.5 1,261
  48. 48 Gemini 3.5 Flash 1,261
  49. 49 GPT-5.6 Terra 1,261
  50. 50 Kimi K2.7 Code 1,259
  51. 51 Mistral Large 4 1,259
  52. 52 GLM-5.3-Flash 1,258
  53. 53 GLM-5-Turbo 1,255
  54. 54 Muse Spark 1,254
  55. 55 Claude Haiku 5.5 1,254
  56. 56 Tencent Hy4 1,253
  57. 57 Claude Opus 4.8 1,251
  58. 58 GPT-5.5 1,249
  59. 59 MiniMax-M3 1,249
  60. 60 GPT-5.6 Luna 1,248
  61. 61 Gemini 3 Pro 1,246
  62. 62 Grok 4.7 1,245
  63. 63 Beam 1.0 max 1,245
  64. 64 Kimi K2.5 thinking 1,242
  65. 65 GLM-5 1,241
  66. 66 Claude Opus 4.5 1,240
  67. 67 MiniMax-M2.7 1,235
  68. 68 Qwen 3.6 Plus 1,235
  69. 69 Deca 2.6 Pro 1,234
  70. 70 DeepSeek V4 Flash 0731 1,231
  71. 71 Mercury 3 1,231
  72. 72 DeepSeek-V4-Pro 1,228
  73. 73 Gemini 3.1 Pro 1,227
  74. 74 GLM-5V-Turbo 1,224
  75. 75 Grok 4.20 Beta reasoning 1,222
  76. 76 Tencent Hy3 1,222
  77. 77 GLM-4.7 1,219
  78. 78 Inkling 1,216
  79. 79 Nex N2 Pro 1,215
  80. 80 MiniMax-M2.5 1,215
  81. 81 GPT-5.4 (Design Skill, Medium) 1,213
  82. 82 GPT-5.4 medium 1,208
  83. 83 DeepSeek-V4-Flash 1,200
  84. 84 MiniMax-M2.1 1,194
  85. 85 Deca 2.6 Mini 1,192
  86. 86 Gemini 3 Flash 1,189
  87. 87 GPT-5.2 xhigh 1,188
  88. 88 glm-4.7-flash 1,187
  89. 89 Grok 4.3 1,187
  90. 90 Step 3.7 Flash 1,187
  91. 91 Muse Glimmer 30B xhigh 1,186
  92. 92 Claude 3.7 Sonnet 1,186
  93. 93 Qwen3.5 397B-A17B 1,184
  94. 94 Claude Sonnet 4.5 thinking 1,183
  95. 95 Qwen3.5 Plus 02-15 1,181
  96. 96 DeepSeek-V3.1 thinking 1,180
  97. 97 GPT-5.1 high 1,180
  98. 98 GPT-5 minimal 1,177
  99. 99 DeepSeek-V3.2-Exp 1,172
  100. 100 Claude Opus 4.1 thinking 1,170
  101. 101 DeepSeek-V3.2 1,168
  102. 102 GLM-4.6 1,167
  103. 103 Solar Pro 4 1,164
  104. 104 GLM-4.5 1,163
  105. 105 Gemini 2.5 Pro Jun 2025 1,160
  106. 106 MiMo-V2-Flash 1,160
  107. 107 Nemotron 3.5 Super VL 1,160
  108. 108 Claude Opus 4 1,158
  109. 109 Flint 1,156
  110. 110 GPT-5.3 Codex 1,156
  111. 111 GPT-5.1-Codex 1,155
  112. 112 Mistral Large 3 1,155
  113. 113 Qwen3 Coder 480B A35B Instruct 1,152
  114. 114 DeepSeek-R1 May 2025 1,142
  115. 115 Solar Mini 4 1,141
  116. 116 v0-1.5-lg 1,139
  117. 117 Claude Sonnet 4 1,139
  118. 118 GLM-4.5-Air 1,139
  119. 119 MiniMax M2 Stable 1,136
  120. 120 Mistral Medium 3.5 1,135
  121. 121 AesCoder-4B 1,134
  122. 122 Nemotron 3 Ultra 1,131
  123. 123 Trinity Large Thinking 1,130
  124. 124 Mistral Medium 3.1 1,126
  125. 125 GPT-5 mini (Default) 1,118
  126. 126 Claude Haiku 4.5 1,115
  127. 127 DeepSeek-V3 Mar 2025 1,113
  128. 128 Qwen3-Max 1,112
  129. 129 Prime Intellect: INTELLECT-3 1,110
  130. 130 Gemini 2.5 Flash Sep 2025 1,108
  131. 131 Grok 4 Fast 1,107
  132. 132 Kimi K2 Thinking 1,106
  133. 133 GPT-5.1-Codex-mini 1,104
  134. 134 AGI-01 Swift 1,100
  135. 135 Kimi K2 0905 Preview 1,100
  136. 136 Grok 4.1 Fast 1,098
  137. 137 GPT-5 nano (Default) 1,094
  138. 138 Gemini 2.5 Flash-Lite Sep 2025 1,092
  139. 139 Kimi K2 Turbo Preview 1,082
  140. 140 Kimi K2 Sep 2025 1,082
  141. 141 Qwen3-Coder-30B-A3B-Instruct 1,080
  142. 142 Gemini 3.1 Flash-Lite 1,076
  143. 143 Ministral 3 14B 1,074
  144. 144 Mistral Medium 3 (2505) 1,072
  145. 145 Ministral 3 8B Instruct 1,058
  146. 146 v0-1.5-md 1,053
  147. 147 Grok 3 1,052
  148. 148 Qwen3-235B-A22B-Instruct-2507 1,051
  149. 149 Qwen3-235B-A22B-Thinking Jul 2025 1,046
  150. 150 Magistral Medium 1.2 (2509) 1,033
  151. 151 GPT-4.1 1,032
  152. 152 o3 1,029
  153. 153 Qwen3-235B-A22B 1,023
  154. 154 Ministral 3 3B Instruct 1,021
  155. 155 Devstral Medium 1,012
  156. 156 Mercury 2 1,011
  157. 157 Grok 4 1,007
  158. 158 Codestral 2508 1,006
  159. 159 GPT-4.1 mini 990
  160. 160 grok-code-fast-1 989
  161. 161 Magistral Small 1.2 (2509) 985
  162. 162 o4-mini 978
  163. 163 Olmo 3.1 32B Think 971
  164. 164 GPT-4.1 nano 966
  165. 165 gpt-oss-120b 961
  166. 166 Qwen3-30B-A3B 948
  167. 167 Llama 3.1 Nemotron Ultra 253B 928
  168. 168 Qwen3 30B-A3B Thinking 2507 923
  169. 169 Grok-3 mini 922
  170. 170 Magistral Small 1.1 905
  171. 171 Mistral Small 3.2 889
  172. 172 Llama 4 Maverick 864
  173. 173 Mistral Large 2.1 (2411) 851
  174. 174 Grok-2 Dec 2024 850
  175. 175 gpt-oss-20b 845
  176. 176 Amazon Nova Premier 828
  177. 177 GPT-4o Mar 2025 824
  178. 178 Codestral 2 (2501) 802
  179. 179 Devstral Small 1.1 795
  180. 180 Amazon Nova Pro 789
  181. 181 Gemini 1.5 Pro Sep 2024 777
  182. 182 Llama 4 Scout 743

Source: Official DesignArena Website leaderboard

151 models. Scroll sideways for the rest. Bars start at 600.

  1. 1,380 Muse Wonder
  2. 1,361 Muse Spark 1.3
  3. 1,352 Claude Fable 5.2
  4. 1,341 GPT-6 Astra
  5. 1,340 Inkling 2 Small
  6. 1,337 Kimi K3
  7. 1,331 Muse Ember
  8. 1,325 Claude Opus 5.5
  9. 1,323 Kimi K3.1 Pro
  10. 1,320 GPT-5.6 Sol
  11. 1,317 Gemini 4 Argon
  12. 1,315 GPT-6.1 Sol
  13. 1,312 MiMo-V2.6 Pro
  14. 1,311 Muse Spark 1.2
  15. 1,311 Claude Sonnet 5.5
  16. 1,308 Muse Spark Open
  17. 1,306 Claude Fable 5.1
  18. 1,305 Claude Opus 5
  19. 1,299 DeepSeek V4.1 Flash
  20. 1,296 Gemini 3.7 Flash
  21. 1,293 Gemini 3.6 Flash
  22. 1,293 Ling-3.1-flash
  23. 1,293 Gemini 4 Carbon
  24. 1,292 Gemini 3.8 Flash
  25. 1,290 GPT-6 Sol
  26. 1,289 Claude Fable 5
  27. 1,287 GPT-6.1 Terra
  28. 1,284 Claude Opus 4.6
  29. 1,280 GLM-5.3
  30. 1,278 Claude Sonnet 4.6
  31. 1,278 GLM-5.2
  32. 1,278 Grok 4.6
  33. 1,278 MiniMax-M3.1-Flash
  34. 1,274 Grok 4.5
  35. 1,270 Qwen 3.8 Max
  36. 1,269 Claude Sonnet 5
  37. 1,269 GPT-6 Luna
  38. 1,268 Qwen3.7-Max
  39. 1,264 Kimi K2.6
  40. 1,264 MiMo-V2.5-Pro
  41. 1,264 Muse Spark 1.1
  42. 1,263 GLM-5.1
  43. 1,262 Qwen3.7-Plus
  44. 1,261 MiMo-V2.5
  45. 1,261 Gemini 3.5 Flash
  46. 1,261 GPT-5.6 Terra
  47. 1,259 Kimi K2.7 Code
  48. 1,259 Mistral Large 4
  49. 1,258 GLM-5.3-Flash
  50. 1,257 Inkling
  51. 1,255 GLM-5-Turbo
  52. 1,254 Muse Spark
  53. 1,254 Claude Haiku 5.5
  54. 1,253 Tencent Hy4
  55. 1,251 Claude Opus 4.8
  56. 1,249 GPT-5.5
  57. 1,249 MiniMax-M3
  58. 1,248 GPT-5.6 Luna
  59. 1,246 Gemini 3 Pro
  60. 1,245 Grok 4.7
  61. 1,245 Beam 1.0
  62. 1,242 Kimi K2.5
  63. 1,241 GLM-5
  64. 1,240 Claude Opus 4.5
  65. 1,235 MiniMax-M2.7
  66. 1,235 Qwen 3.6 Plus
  67. 1,231 DeepSeek V4 Flash 0731
  68. 1,231 Mercury 3
  69. 1,228 DeepSeek-V4-Pro
  70. 1,227 Gemini 3.1 Pro
  71. 1,224 GLM-5V-Turbo
  72. 1,222 Tencent Hy3
  73. 1,219 GLM-4.7
  74. 1,215 MiniMax-M2.5
  75. 1,208 GPT-5.4
  76. 1,200 DeepSeek-V4-Flash
  77. 1,194 MiniMax-M2.1
  78. 1,189 Gemini 3 Flash
  79. 1,188 GPT-5.2
  80. 1,187 glm-4.7-flash
  81. 1,187 Grok 4.3
  82. 1,187 Step 3.7 Flash
  83. 1,186 Claude 3.7 Sonnet
  84. 1,184 Qwen3.5 397B-A17B
  85. 1,183 Claude Sonnet 4.5
  86. 1,180 DeepSeek-V3.1
  87. 1,180 GPT-5.1
  88. 1,177 GPT-5
  89. 1,172 DeepSeek-V3.2-Exp
  90. 1,170 Claude Opus 4.1
  91. 1,168 DeepSeek-V3.2
  92. 1,167 GLM-4.6
  93. 1,164 Solar Pro 4
  94. 1,163 GLM-4.5
  95. 1,160 Gemini 2.5 Pro
  96. 1,160 MiMo-V2-Flash
  97. 1,160 Nemotron 3.5 Super VL
  98. 1,158 Claude Opus 4
  99. 1,156 GPT-5.3 Codex
  100. 1,155 GPT-5.1-Codex
  101. 1,155 Mistral Large 3
  102. 1,142 DeepSeek-R1
  103. 1,141 Solar Mini 4
  104. 1,139 Claude Sonnet 4
  105. 1,139 GLM-4.5-Air
  106. 1,135 Mistral Medium 3.5
  107. 1,131 Nemotron 3 Ultra
  108. 1,130 Trinity Large Thinking
  109. 1,126 Mistral Medium 3.1
  110. 1,115 Claude Haiku 4.5
  111. 1,113 DeepSeek-V3
  112. 1,112 Qwen3-Max
  113. 1,108 Gemini 2.5 Flash
  114. 1,107 Grok 4 Fast
  115. 1,106 Kimi K2 Thinking
  116. 1,104 GPT-5.1-Codex-mini
  117. 1,098 Grok 4.1 Fast
  118. 1,092 Gemini 2.5 Flash-Lite
  119. 1,082 Kimi K2
  120. 1,080 Qwen3-Coder-30B-A3B-Instruct
  121. 1,076 Gemini 3.1 Flash-Lite
  122. 1,074 Ministral 3 14B
  123. 1,058 Ministral 3 8B Instruct
  124. 1,052 Grok 3
  125. 1,046 Qwen3-235B-A22B-Thinking
  126. 1,032 GPT-4.1
  127. 1,029 o3
  128. 1,023 Qwen3-235B-A22B
  129. 1,021 Ministral 3 3B Instruct
  130. 1,012 Devstral Medium
  131. 1,011 Mercury 2
  132. 1,007 Grok 4
  133. 990 GPT-4.1 mini
  134. 989 grok-code-fast-1
  135. 978 o4-mini
  136. 971 Olmo 3.1 32B Think
  137. 966 GPT-4.1 nano
  138. 961 gpt-oss-120b
  139. 948 Qwen3-30B-A3B
  140. 922 Grok-3 mini
  141. 905 Magistral Small 1.1
  142. 889 Mistral Small 3.2
  143. 864 Llama 4 Maverick
  144. 850 Grok-2
  145. 845 gpt-oss-20b
  146. 828 Amazon Nova Premier
  147. 824 GPT-4o
  148. 795 Devstral Small 1.1
  149. 789 Amazon Nova Pro
  150. 777 Gemini 1.5 Pro
  151. 743 Llama 4 Scout

Bars start at 600.

  1. 1 Muse Wonder max 1,380
  2. 2 Muse Spark 1.3 xhigh 1,361
  3. 3 Claude Fable 5.2 1,352
  4. 4 GPT-6 Astra xhigh 1,341
  5. 5 Inkling 2 Small 1,340
  6. 6 Kimi K3 1,337
  7. 7 Muse Ember 1,331
  8. 8 Claude Opus 5.5 1,325
  9. 9 Kimi K3.1 Pro 1,323
  10. 10 GPT-5.6 Sol medium, xhigh 1,320
  11. 11 Gemini 4 Argon 1,317
  12. 12 GPT-6.1 Sol 1,315
  13. 13 MiMo-V2.6 Pro 1,312
  14. 14 Muse Spark 1.2 1,311
  15. 15 Claude Sonnet 5.5 1,311
  16. 16 Muse Spark Open xhigh 1,308
  17. 17 Claude Fable 5.1 1,306
  18. 18 Claude Opus 5 1,305
  19. 19 DeepSeek V4.1 Flash 1,299
  20. 20 Gemini 3.7 Flash 1,296
  21. 21 Gemini 3.6 Flash 1,293
  22. 22 Ling-3.1-flash 1,293
  23. 23 Gemini 4 Carbon 1,293
  24. 24 Gemini 3.8 Flash 1,292
  25. 25 GPT-6 Sol 1,290
  26. 26 Claude Fable 5 1,289
  27. 27 GPT-6.1 Terra 1,287
  28. 28 Claude Opus 4.6 1,284
  29. 29 GLM-5.3 1,280
  30. 30 Claude Sonnet 4.6 1,278
  31. 31 GLM-5.2 1,278
  32. 32 Grok 4.6 1,278
  33. 33 MiniMax-M3.1-Flash 1,278
  34. 34 Grok 4.5 1,274
  35. 35 Qwen 3.8 Max 1,270
  36. 36 Claude Sonnet 5 1,269
  37. 37 GPT-6 Luna 1,269
  38. 38 Qwen3.7-Max 1,268
  39. 39 Kimi K2.6 1,264
  40. 40 MiMo-V2.5-Pro 1,264
  41. 41 Muse Spark 1.1 1,264
  42. 42 GLM-5.1 1,263
  43. 43 Qwen3.7-Plus 1,262
  44. 44 MiMo-V2.5 1,261
  45. 45 Gemini 3.5 Flash 1,261
  46. 46 GPT-5.6 Terra 1,261
  47. 47 Kimi K2.7 Code 1,259
  48. 48 Mistral Large 4 1,259
  49. 49 GLM-5.3-Flash 1,258
  50. 50 Inkling 1,257
  51. 51 GLM-5-Turbo 1,255
  52. 52 Muse Spark 1,254
  53. 53 Claude Haiku 5.5 1,254
  54. 54 Tencent Hy4 1,253
  55. 55 Claude Opus 4.8 1,251
  56. 56 GPT-5.5 1,249
  57. 57 MiniMax-M3 1,249
  58. 58 GPT-5.6 Luna 1,248
  59. 59 Gemini 3 Pro 1,246
  60. 60 Grok 4.7 1,245
  61. 61 Beam 1.0 max 1,245
  62. 62 Kimi K2.5 thinking 1,242
  63. 63 GLM-5 1,241
  64. 64 Claude Opus 4.5 1,240
  65. 65 MiniMax-M2.7 1,235
  66. 66 Qwen 3.6 Plus 1,235
  67. 67 DeepSeek V4 Flash 0731 1,231
  68. 68 Mercury 3 1,231
  69. 69 DeepSeek-V4-Pro 1,228
  70. 70 Gemini 3.1 Pro 1,227
  71. 71 GLM-5V-Turbo 1,224
  72. 72 Tencent Hy3 1,222
  73. 73 GLM-4.7 1,219
  74. 74 MiniMax-M2.5 1,215
  75. 75 GPT-5.4 medium 1,208
  76. 76 DeepSeek-V4-Flash 1,200
  77. 77 MiniMax-M2.1 1,194
  78. 78 Gemini 3 Flash 1,189
  79. 79 GPT-5.2 xhigh 1,188
  80. 80 glm-4.7-flash 1,187
  81. 81 Grok 4.3 1,187
  82. 82 Step 3.7 Flash 1,187
  83. 83 Claude 3.7 Sonnet 1,186
  84. 84 Qwen3.5 397B-A17B 1,184
  85. 85 Claude Sonnet 4.5 thinking 1,183
  86. 86 DeepSeek-V3.1 thinking 1,180
  87. 87 GPT-5.1 high 1,180
  88. 88 GPT-5 minimal 1,177
  89. 89 DeepSeek-V3.2-Exp 1,172
  90. 90 Claude Opus 4.1 thinking 1,170
  91. 91 DeepSeek-V3.2 1,168
  92. 92 GLM-4.6 1,167
  93. 93 Solar Pro 4 1,164
  94. 94 GLM-4.5 1,163
  95. 95 Gemini 2.5 Pro Jun 2025 1,160
  96. 96 MiMo-V2-Flash 1,160
  97. 97 Nemotron 3.5 Super VL 1,160
  98. 98 Claude Opus 4 1,158
  99. 99 GPT-5.3 Codex 1,156
  100. 100 GPT-5.1-Codex 1,155
  101. 101 Mistral Large 3 1,155
  102. 102 DeepSeek-R1 May 2025 1,142
  103. 103 Solar Mini 4 1,141
  104. 104 Claude Sonnet 4 1,139
  105. 105 GLM-4.5-Air 1,139
  106. 106 Mistral Medium 3.5 1,135
  107. 107 Nemotron 3 Ultra 1,131
  108. 108 Trinity Large Thinking 1,130
  109. 109 Mistral Medium 3.1 1,126
  110. 110 Claude Haiku 4.5 1,115
  111. 111 DeepSeek-V3 Mar 2025 1,113
  112. 112 Qwen3-Max 1,112
  113. 113 Gemini 2.5 Flash Sep 2025 1,108
  114. 114 Grok 4 Fast 1,107
  115. 115 Kimi K2 Thinking 1,106
  116. 116 GPT-5.1-Codex-mini 1,104
  117. 117 Grok 4.1 Fast 1,098
  118. 118 Gemini 2.5 Flash-Lite Sep 2025 1,092
  119. 119 Kimi K2 Sep 2025 1,082
  120. 120 Qwen3-Coder-30B-A3B-Instruct 1,080
  121. 121 Gemini 3.1 Flash-Lite 1,076
  122. 122 Ministral 3 14B 1,074
  123. 123 Ministral 3 8B Instruct 1,058
  124. 124 Grok 3 1,052
  125. 125 Qwen3-235B-A22B-Thinking Jul 2025 1,046
  126. 126 GPT-4.1 1,032
  127. 127 o3 1,029
  128. 128 Qwen3-235B-A22B 1,023
  129. 129 Ministral 3 3B Instruct 1,021
  130. 130 Devstral Medium 1,012
  131. 131 Mercury 2 1,011
  132. 132 Grok 4 1,007
  133. 133 GPT-4.1 mini 990
  134. 134 grok-code-fast-1 989
  135. 135 o4-mini 978
  136. 136 Olmo 3.1 32B Think 971
  137. 137 GPT-4.1 nano 966
  138. 138 gpt-oss-120b 961
  139. 139 Qwen3-30B-A3B 948
  140. 140 Grok-3 mini 922
  141. 141 Magistral Small 1.1 905
  142. 142 Mistral Small 3.2 889
  143. 143 Llama 4 Maverick 864
  144. 144 Grok-2 Dec 2024 850
  145. 145 gpt-oss-20b 845
  146. 146 Amazon Nova Premier 828
  147. 147 GPT-4o Mar 2025 824
  148. 148 Devstral Small 1.1 795
  149. 149 Amazon Nova Pro 789
  150. 150 Gemini 1.5 Pro Sep 2024 777
  151. 151 Llama 4 Scout 743

Sources: Official DesignArena Website leaderboard and labs’ model cards

#EntryScoreSettingDateSource
1 Muse Wonder 1,380 max Oct 2026 Official leaderboard
2 Muse Spark 1.3 1,361 xhigh Sep 2026 Official leaderboard
3 Claude Fable 5.2 1,352 Nov 2026 Official leaderboard
4 GPT-6 Astra 1,341 xhigh Sep 2026 Official leaderboard
5 Kimi K3 1,337 Jul 2026 Official leaderboard
6 Inkling 2 Small 1,332 Nov 2026 Official leaderboard
7 Muse Ember 1,331 Nov 2026 Official leaderboard
8 Claude Opus 5.5 1,325 Sep 2026 Official leaderboard
9 Kimi K3.1 Pro 1,323 Oct 2026 Official leaderboard
10 GPT-5.6 Sol 1,320 medium, xhigh Jul 2026 Official leaderboard
11 Gemini 4 Argon 1,317 Sep 2026 Official leaderboard
12 GPT-6.1 Sol 1,315 Sep 2026 Official leaderboard
13 MiMo-V2.6 Pro 1,312 Sep 2026 Official leaderboard
14 Muse Spark 1.2 1,311 Aug 2026 Official leaderboard
15 Claude Sonnet 5.5 1,311 Sep 2026 Official leaderboard
16 Muse Spark Open 1,308 xhigh Oct 2026 Official leaderboard
17 Claude Fable 5.1 1,306 Sep 2026 Official leaderboard
18 Claude Opus 5 1,305 Jul 2026 Official leaderboard
19 DeepSeek V4.1 Flash 1,299 Sep 2026 Official leaderboard
20 Gemini 3.7 Flash 1,296 Aug 2026 Official leaderboard
21 Gemini 3.6 Flash 1,293 Jul 2026 Official leaderboard
22 Ling-3.1-flash 1,293 Oct 2026 Official leaderboard
23 Gemini 4 Carbon 1,293 Oct 2026 Official leaderboard
24 Gemini 3.8 Flash 1,292 Sep 2026 Official leaderboard
25 GPT-6 Sol 1,290 Sep 2026 Official leaderboard
26 Claude Fable 5 1,289 Jun 2026 Official leaderboard
27 GPT-6.1 Terra 1,287 Oct 2026 Official leaderboard
28 Claude Opus 4.6 1,284 Feb 2026 Official leaderboard
29 GLM-5.3 1,280 Aug 2026 Official leaderboard
30 Deca 2.5 Mini 1,278 Official leaderboard
31 Claude Sonnet 4.6 1,278 Feb 2026 Official leaderboard
32 GLM-5.2 1,278 Jun 2026 Official leaderboard
33 Grok 4.6 1,278 Aug 2026 Official leaderboard
34 MiniMax-M3.1-Flash 1,278 Oct 2026 Official leaderboard
35 Grok 4.5 1,274 Jul 2026 Official leaderboard
36 Deca 2.6 Ultra 1,273 Official leaderboard
37 Qwen 3.8 Max 1,270 Aug 2026 Official leaderboard
38 Claude Sonnet 5 1,269 Jun 2026 Official leaderboard
39 GPT-6 Luna 1,269 Sep 2026 Official leaderboard
40 Qwen3.7-Max 1,268 May 2026 Official leaderboard
41 Deca 2.5 Ultra 1,266 2 Official leaderboard
42 Kimi K2.6 1,264 Apr 2026 Official leaderboard
43 MiMo-V2.5-Pro 1,264 Apr 2026 Official leaderboard
44 Muse Spark 1.1 1,264 Jul 2026 Official leaderboard
45 GLM-5.1 1,263 Apr 2026 Official leaderboard
46 Qwen3.7-Plus 1,262 Jun 2026 Official leaderboard
47 MiMo-V2.5 1,261 Apr 2026 Official leaderboard
48 Gemini 3.5 Flash 1,261 May 2026 Official leaderboard
49 GPT-5.6 Terra 1,261 Jul 2026 Official leaderboard
50 Kimi K2.7 Code 1,259 Jun 2026 Official leaderboard
51 Mistral Large 4 1,259 Oct 2026 Official leaderboard
52 GLM-5.3-Flash 1,258 Aug 2026 Official leaderboard
53 GLM-5-Turbo 1,255 Mar 2026 Official leaderboard
54 Muse Spark 1,254 Apr 2026 Official leaderboard
55 Claude Haiku 5.5 1,254 Oct 2026 Official leaderboard
56 Tencent Hy4 1,253 Nov 2026 Official leaderboard
57 Claude Opus 4.8 1,251 May 2026 Official leaderboard
58 GPT-5.5 1,249 Apr 2026 Official leaderboard
59 MiniMax-M3 1,249 Jun 2026 Official leaderboard
60 GPT-5.6 Luna 1,248 Jul 2026 Official leaderboard
61 Gemini 3 Pro 1,246 Nov 2025 Official leaderboard
62 Grok 4.7 1,245 Sep 2026 Official leaderboard
63 Beam 1.0 1,245 max Oct 2026 Official leaderboard
64 Kimi K2.5 1,242 thinking Jan 2026 Official leaderboard
65 GLM-5 1,241 Feb 2026 Official leaderboard
66 Claude Opus 4.5 1,240 Nov 2025 Official leaderboard
67 MiniMax-M2.7 1,235 Mar 2026 Official leaderboard
68 Qwen 3.6 Plus 1,235 Mar 2026 Official leaderboard
69 Deca 2.6 Pro 1,234 Official leaderboard
70 DeepSeek V4 Flash 0731 1,231 Jul 2026 Official leaderboard
71 Mercury 3 1,231 Oct 2026 Official leaderboard
72 DeepSeek-V4-Pro 1,228 Apr 2026 Official leaderboard
73 Gemini 3.1 Pro 1,227 Feb 2026 Official leaderboard
74 GLM-5V-Turbo 1,224 Apr 2026 Official leaderboard
75 Grok 4.20 Beta 1,222 reasoning Official leaderboard
76 Tencent Hy3 1,222 Jul 2026 Official leaderboard
77 GLM-4.7 1,219 Dec 2025 Official leaderboard
78 Inkling 1,216 Jul 2026 Official leaderboard
79 Nex N2 Pro 1,215 Official leaderboard
80 MiniMax-M2.5 1,215 Feb 2026 Official leaderboard
81 GPT-5.4 (Design Skill, Medium) 1,213 Official leaderboard
82 GPT-5.4 1,208 medium Mar 2026 Official leaderboard
83 DeepSeek-V4-Flash 1,200 Apr 2026 Official leaderboard
84 MiniMax-M2.1 1,194 Dec 2025 Official leaderboard
85 Deca 2.6 Mini 1,192 Official leaderboard
86 Gemini 3 Flash 1,189 Dec 2025 Official leaderboard
87 GPT-5.2 1,188 xhigh Dec 2025 Official leaderboard
88 glm-4.7-flash 1,187 Jan 2026 Official leaderboard
89 Grok 4.3 1,187 Apr 2026 Official leaderboard
90 Step 3.7 Flash 1,187 May 2026 Official leaderboard
91 Muse Glimmer 30B 1,186 xhigh Official leaderboard
92 Claude 3.7 Sonnet 1,186 Feb 2025 Official leaderboard
93 Qwen3.5 397B-A17B 1,184 Feb 2026 Official leaderboard
94 Claude Sonnet 4.5 1,183 thinking Sep 2025 Official leaderboard
95 Qwen3.5 Plus 02-15 1,181 Official leaderboard
96 DeepSeek-V3.1 1,180 thinking Aug 2025 Official leaderboard
97 GPT-5.1 1,180 high Nov 2025 Official leaderboard
98 GPT-5 1,177 minimal Aug 2025 Official leaderboard
99 DeepSeek-V3.2-Exp 1,172 Sep 2025 Official leaderboard
100 Claude Opus 4.1 1,170 thinking Aug 2025 Official leaderboard
101 DeepSeek-V3.2 1,168 Dec 2025 Official leaderboard
102 GLM-4.6 1,167 Sep 2025 Official leaderboard
103 Solar Pro 4 1,164 Aug 2026 Official leaderboard
104 GLM-4.5 1,163 Aug 2025 Official leaderboard
105 Gemini 2.5 Pro Jun 2025 1,160 Jun 2025 Official leaderboard
106 MiMo-V2-Flash 1,160 Dec 2025 Official leaderboard
107 Nemotron 3.5 Super VL 1,160 Oct 2026 Official leaderboard
108 Claude Opus 4 1,158 May 2025 Official leaderboard
109 Flint 1,156 Official leaderboard
110 GPT-5.3 Codex 1,156 Feb 2026 Official leaderboard
111 GPT-5.1-Codex 1,155 Nov 2025 Official leaderboard
112 Mistral Large 3 1,155 Dec 2025 Official leaderboard
113 Qwen3 Coder 480B A35B Instruct 1,152 Official leaderboard
114 DeepSeek-R1 May 2025 1,142 May 2025 Official leaderboard
115 Solar Mini 4 1,141 Oct 2026 Official leaderboard
116 v0-1.5-lg 1,139 Official leaderboard
117 Claude Sonnet 4 1,139 May 2025 Official leaderboard
118 GLM-4.5-Air 1,139 Jul 2025 Official leaderboard
119 MiniMax M2 Stable 1,136 Official leaderboard
120 Mistral Medium 3.5 1,135 Apr 2026 Official leaderboard
121 AesCoder-4B 1,134 Official leaderboard
122 Nemotron 3 Ultra 1,131 Jun 2026 Official leaderboard
123 Trinity Large Thinking 1,130 Apr 2026 Official leaderboard
124 Mistral Medium 3.1 1,126 Aug 2025 Official leaderboard
125 GPT-5 mini (Default) 1,118 Official leaderboard
126 Claude Haiku 4.5 1,115 Oct 2025 Official leaderboard
127 DeepSeek-V3 Mar 2025 1,113 Mar 2025 Official leaderboard
128 Qwen3-Max 1,112 Sep 2025 Official leaderboard
129 Prime Intellect: INTELLECT-3 1,110 Official leaderboard
130 Gemini 2.5 Flash Sep 2025 1,108 Sep 2025 Official leaderboard
131 Grok 4 Fast 1,107 Sep 2025 Official leaderboard
132 Kimi K2 Thinking 1,106 Nov 2025 Official leaderboard
133 GPT-5.1-Codex-mini 1,104 Nov 2025 Official leaderboard
134 AGI-01 Swift 1,100 Official leaderboard
135 Kimi K2 0905 Preview 1,100 Official leaderboard
136 Grok 4.1 Fast 1,098 Nov 2025 Official leaderboard
137 GPT-5 nano (Default) 1,094 Official leaderboard
138 Gemini 2.5 Flash-Lite Sep 2025 1,092 Sep 2025 Official leaderboard
139 Kimi K2 Turbo Preview 1,082 Official leaderboard
140 Kimi K2 Sep 2025 1,082 Sep 2025 Official leaderboard
141 Qwen3-Coder-30B-A3B-Instruct 1,080 Jul 2025 Official leaderboard
142 Gemini 3.1 Flash-Lite 1,076 Mar 2026 Official leaderboard
143 Ministral 3 14B 1,074 Dec 2025 Official leaderboard
144 Mistral Medium 3 (2505) 1,072 Official leaderboard
145 Ministral 3 8B Instruct 1,058 Dec 2025 Official leaderboard
146 v0-1.5-md 1,053 Official leaderboard
147 Grok 3 1,052 Apr 2025 Official leaderboard
148 Qwen3-235B-A22B-Instruct-2507 1,051 Official leaderboard
149 Qwen3-235B-A22B-Thinking Jul 2025 1,046 Jul 2025 Official leaderboard
150 Magistral Medium 1.2 (2509) 1,033 Official leaderboard
151 GPT-4.1 1,032 Apr 2025 Official leaderboard
152 o3 1,029 Apr 2025 Official leaderboard
153 Qwen3-235B-A22B 1,023 Apr 2025 Official leaderboard
154 Ministral 3 3B Instruct 1,021 Dec 2025 Official leaderboard
155 Devstral Medium 1,012 Jul 2025 Official leaderboard
156 Mercury 2 1,011 Feb 2026 Official leaderboard
157 Grok 4 1,007 Jul 2025 Official leaderboard
158 Codestral 2508 1,006 Official leaderboard
159 GPT-4.1 mini 990 Apr 2025 Official leaderboard
160 grok-code-fast-1 989 Aug 2025 Official leaderboard
161 Magistral Small 1.2 (2509) 985 Official leaderboard
162 o4-mini 978 Apr 2025 Official leaderboard
163 Olmo 3.1 32B Think 971 Dec 2025 Official leaderboard
164 GPT-4.1 nano 966 Apr 2025 Official leaderboard
165 gpt-oss-120b 961 Aug 2025 Official leaderboard
166 Qwen3-30B-A3B 948 Apr 2025 Official leaderboard
167 Llama 3.1 Nemotron Ultra 253B 928 Official leaderboard
168 Qwen3 30B-A3B Thinking 2507 923 Official leaderboard
169 Grok-3 mini 922 Apr 2025 Official leaderboard
170 Magistral Small 1.1 905 Jul 2025 Official leaderboard
171 Mistral Small 3.2 889 Jun 2025 Official leaderboard
172 Llama 4 Maverick 864 Apr 2025 Official leaderboard
173 Mistral Large 2.1 (2411) 851 Official leaderboard
174 Grok-2 Dec 2024 850 Dec 2024 Official leaderboard
175 gpt-oss-20b 845 Aug 2025 Official leaderboard
176 Amazon Nova Premier 828 Apr 2025 Official leaderboard
177 GPT-4o Mar 2025 824 Mar 2025 Official leaderboard
178 Codestral 2 (2501) 802 Official leaderboard
179 Devstral Small 1.1 795 Jul 2025 Official leaderboard
180 Amazon Nova Pro 789 Dec 2024 Official leaderboard
181 Gemini 1.5 Pro Sep 2024 777 Sep 2024 Official leaderboard
182 Llama 4 Scout 743 Apr 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Muse Wonder 1,380 max Oct 2026 Official leaderboard
2 Muse Spark 1.3 1,361 xhigh Sep 2026 Official leaderboard
3 Claude Fable 5.2 1,352 Nov 2026 Official leaderboard
4 GPT-6 Astra 1,341 xhigh Sep 2026 Official leaderboard
5 Inkling 2 Small 1,340 Nov 2026 Lab model card
6 Kimi K3 1,337 Jul 2026 Official leaderboard
7 Muse Ember 1,331 Nov 2026 Official leaderboard
8 Claude Opus 5.5 1,325 Sep 2026 Official leaderboard
9 Kimi K3.1 Pro 1,323 Oct 2026 Official leaderboard
10 GPT-5.6 Sol 1,320 medium, xhigh Jul 2026 Official leaderboard
11 Gemini 4 Argon 1,317 Sep 2026 Official leaderboard
12 GPT-6.1 Sol 1,315 Sep 2026 Official leaderboard
13 MiMo-V2.6 Pro 1,312 Sep 2026 Official leaderboard
14 Muse Spark 1.2 1,311 Aug 2026 Official leaderboard
15 Claude Sonnet 5.5 1,311 Sep 2026 Official leaderboard
16 Muse Spark Open 1,308 xhigh Oct 2026 Official leaderboard
17 Claude Fable 5.1 1,306 Sep 2026 Official leaderboard
18 Claude Opus 5 1,305 Jul 2026 Official leaderboard
19 DeepSeek V4.1 Flash 1,299 Sep 2026 Official leaderboard
20 Gemini 3.7 Flash 1,296 Aug 2026 Official leaderboard
21 Gemini 3.6 Flash 1,293 Jul 2026 Official leaderboard
22 Ling-3.1-flash 1,293 Oct 2026 Official leaderboard
23 Gemini 4 Carbon 1,293 Oct 2026 Official leaderboard
24 Gemini 3.8 Flash 1,292 Sep 2026 Official leaderboard
25 GPT-6 Sol 1,290 Sep 2026 Official leaderboard
26 Claude Fable 5 1,289 Jun 2026 Official leaderboard
27 GPT-6.1 Terra 1,287 Oct 2026 Official leaderboard
28 Claude Opus 4.6 1,284 Feb 2026 Official leaderboard
29 GLM-5.3 1,280 Aug 2026 Official leaderboard
30 Claude Sonnet 4.6 1,278 Feb 2026 Official leaderboard
31 GLM-5.2 1,278 Jun 2026 Official leaderboard
32 Grok 4.6 1,278 Aug 2026 Official leaderboard
33 MiniMax-M3.1-Flash 1,278 Oct 2026 Official leaderboard
34 Grok 4.5 1,274 Jul 2026 Official leaderboard
35 Qwen 3.8 Max 1,270 Aug 2026 Official leaderboard
36 Claude Sonnet 5 1,269 Jun 2026 Official leaderboard
37 GPT-6 Luna 1,269 Sep 2026 Official leaderboard
38 Qwen3.7-Max 1,268 May 2026 Official leaderboard
39 Kimi K2.6 1,264 Apr 2026 Official leaderboard
40 MiMo-V2.5-Pro 1,264 Apr 2026 Official leaderboard
41 Muse Spark 1.1 1,264 Jul 2026 Official leaderboard
42 GLM-5.1 1,263 Apr 2026 Official leaderboard
43 Qwen3.7-Plus 1,262 Jun 2026 Official leaderboard
44 MiMo-V2.5 1,261 Apr 2026 Official leaderboard
45 Gemini 3.5 Flash 1,261 May 2026 Official leaderboard
46 GPT-5.6 Terra 1,261 Jul 2026 Official leaderboard
47 Kimi K2.7 Code 1,259 Jun 2026 Official leaderboard
48 Mistral Large 4 1,259 Oct 2026 Official leaderboard
49 GLM-5.3-Flash 1,258 Aug 2026 Official leaderboard
50 Inkling 1,257 Jul 2026 Lab model card
51 GLM-5-Turbo 1,255 Mar 2026 Official leaderboard
52 Muse Spark 1,254 Apr 2026 Official leaderboard
53 Claude Haiku 5.5 1,254 Oct 2026 Official leaderboard
54 Tencent Hy4 1,253 Nov 2026 Official leaderboard
55 Claude Opus 4.8 1,251 May 2026 Official leaderboard
56 GPT-5.5 1,249 Apr 2026 Official leaderboard
57 MiniMax-M3 1,249 Jun 2026 Official leaderboard
58 GPT-5.6 Luna 1,248 Jul 2026 Official leaderboard
59 Gemini 3 Pro 1,246 Nov 2025 Official leaderboard
60 Grok 4.7 1,245 Sep 2026 Official leaderboard
61 Beam 1.0 1,245 max Oct 2026 Official leaderboard
62 Kimi K2.5 1,242 thinking Jan 2026 Official leaderboard
63 GLM-5 1,241 Feb 2026 Official leaderboard
64 Claude Opus 4.5 1,240 Nov 2025 Official leaderboard
65 MiniMax-M2.7 1,235 Mar 2026 Official leaderboard
66 Qwen 3.6 Plus 1,235 Mar 2026 Official leaderboard
67 DeepSeek V4 Flash 0731 1,231 Jul 2026 Official leaderboard
68 Mercury 3 1,231 Oct 2026 Official leaderboard
69 DeepSeek-V4-Pro 1,228 Apr 2026 Official leaderboard
70 Gemini 3.1 Pro 1,227 Feb 2026 Official leaderboard
71 GLM-5V-Turbo 1,224 Apr 2026 Official leaderboard
72 Tencent Hy3 1,222 Jul 2026 Official leaderboard
73 GLM-4.7 1,219 Dec 2025 Official leaderboard
74 MiniMax-M2.5 1,215 Feb 2026 Official leaderboard
75 GPT-5.4 1,208 medium Mar 2026 Official leaderboard
76 DeepSeek-V4-Flash 1,200 Apr 2026 Official leaderboard
77 MiniMax-M2.1 1,194 Dec 2025 Official leaderboard
78 Gemini 3 Flash 1,189 Dec 2025 Official leaderboard
79 GPT-5.2 1,188 xhigh Dec 2025 Official leaderboard
80 glm-4.7-flash 1,187 Jan 2026 Official leaderboard
81 Grok 4.3 1,187 Apr 2026 Official leaderboard
82 Step 3.7 Flash 1,187 May 2026 Official leaderboard
83 Claude 3.7 Sonnet 1,186 Feb 2025 Official leaderboard
84 Qwen3.5 397B-A17B 1,184 Feb 2026 Official leaderboard
85 Claude Sonnet 4.5 1,183 thinking Sep 2025 Official leaderboard
86 DeepSeek-V3.1 1,180 thinking Aug 2025 Official leaderboard
87 GPT-5.1 1,180 high Nov 2025 Official leaderboard
88 GPT-5 1,177 minimal Aug 2025 Official leaderboard
89 DeepSeek-V3.2-Exp 1,172 Sep 2025 Official leaderboard
90 Claude Opus 4.1 1,170 thinking Aug 2025 Official leaderboard
91 DeepSeek-V3.2 1,168 Dec 2025 Official leaderboard
92 GLM-4.6 1,167 Sep 2025 Official leaderboard
93 Solar Pro 4 1,164 Aug 2026 Official leaderboard
94 GLM-4.5 1,163 Aug 2025 Official leaderboard
95 Gemini 2.5 Pro Jun 2025 1,160 Jun 2025 Official leaderboard
96 MiMo-V2-Flash 1,160 Dec 2025 Official leaderboard
97 Nemotron 3.5 Super VL 1,160 Oct 2026 Official leaderboard
98 Claude Opus 4 1,158 May 2025 Official leaderboard
99 GPT-5.3 Codex 1,156 Feb 2026 Official leaderboard
100 GPT-5.1-Codex 1,155 Nov 2025 Official leaderboard
101 Mistral Large 3 1,155 Dec 2025 Official leaderboard
102 DeepSeek-R1 May 2025 1,142 May 2025 Official leaderboard
103 Solar Mini 4 1,141 Oct 2026 Official leaderboard
104 Claude Sonnet 4 1,139 May 2025 Official leaderboard
105 GLM-4.5-Air 1,139 Jul 2025 Official leaderboard
106 Mistral Medium 3.5 1,135 Apr 2026 Official leaderboard
107 Nemotron 3 Ultra 1,131 Jun 2026 Official leaderboard
108 Trinity Large Thinking 1,130 Apr 2026 Official leaderboard
109 Mistral Medium 3.1 1,126 Aug 2025 Official leaderboard
110 Claude Haiku 4.5 1,115 Oct 2025 Official leaderboard
111 DeepSeek-V3 Mar 2025 1,113 Mar 2025 Official leaderboard
112 Qwen3-Max 1,112 Sep 2025 Official leaderboard
113 Gemini 2.5 Flash Sep 2025 1,108 Sep 2025 Official leaderboard
114 Grok 4 Fast 1,107 Sep 2025 Official leaderboard
115 Kimi K2 Thinking 1,106 Nov 2025 Official leaderboard
116 GPT-5.1-Codex-mini 1,104 Nov 2025 Official leaderboard
117 Grok 4.1 Fast 1,098 Nov 2025 Official leaderboard
118 Gemini 2.5 Flash-Lite Sep 2025 1,092 Sep 2025 Official leaderboard
119 Kimi K2 Sep 2025 1,082 Sep 2025 Official leaderboard
120 Qwen3-Coder-30B-A3B-Instruct 1,080 Jul 2025 Official leaderboard
121 Gemini 3.1 Flash-Lite 1,076 Mar 2026 Official leaderboard
122 Ministral 3 14B 1,074 Dec 2025 Official leaderboard
123 Ministral 3 8B Instruct 1,058 Dec 2025 Official leaderboard
124 Grok 3 1,052 Apr 2025 Official leaderboard
125 Qwen3-235B-A22B-Thinking Jul 2025 1,046 Jul 2025 Official leaderboard
126 GPT-4.1 1,032 Apr 2025 Official leaderboard
127 o3 1,029 Apr 2025 Official leaderboard
128 Qwen3-235B-A22B 1,023 Apr 2025 Official leaderboard
129 Ministral 3 3B Instruct 1,021 Dec 2025 Official leaderboard
130 Devstral Medium 1,012 Jul 2025 Official leaderboard
131 Mercury 2 1,011 Feb 2026 Official leaderboard
132 Grok 4 1,007 Jul 2025 Official leaderboard
133 GPT-4.1 mini 990 Apr 2025 Official leaderboard
134 grok-code-fast-1 989 Aug 2025 Official leaderboard
135 o4-mini 978 Apr 2025 Official leaderboard
136 Olmo 3.1 32B Think 971 Dec 2025 Official leaderboard
137 GPT-4.1 nano 966 Apr 2025 Official leaderboard
138 gpt-oss-120b 961 Aug 2025 Official leaderboard
139 Qwen3-30B-A3B 948 Apr 2025 Official leaderboard
140 Grok-3 mini 922 Apr 2025 Official leaderboard
141 Magistral Small 1.1 905 Jul 2025 Official leaderboard
142 Mistral Small 3.2 889 Jun 2025 Official leaderboard
143 Llama 4 Maverick 864 Apr 2025 Official leaderboard
144 Grok-2 Dec 2024 850 Dec 2024 Official leaderboard
145 gpt-oss-20b 845 Aug 2025 Official leaderboard
146 Amazon Nova Premier 828 Apr 2025 Official leaderboard
147 GPT-4o Mar 2025 824 Mar 2025 Official leaderboard
148 Devstral Small 1.1 795 Jul 2025 Official leaderboard
149 Amazon Nova Pro 789 Dec 2024 Official leaderboard
150 Gemini 1.5 Pro Sep 2024 777 Sep 2024 Official leaderboard
151 Llama 4 Scout 743 Apr 2025 Official leaderboard

Labs report scores for 2 models in their cards. Switch the scores above to rank them together.

More effort adds a median 11 elo

Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.

Lowest effort to highest, light to dark
Muse Spark 1.3
xhigh, max
1,361
GPT-6 Astra
xhigh, max
1,341
GPT-5.6 Sol
medium
1,320
DeepSeek V4.1 Flash
1017
1,299
Claude Opus 4.6
thinking
1,284
Tencent Hy3
low
1,222
GPT-5.4
none
1,208
GPT-5.2
none high xhigh
1,188
Claude Sonnet 4.5
thinking
1,183
DeepSeek-V3.1
thinking
1,180
GPT-5.1
none
1,180
GPT-5
minimal, hi…
1,177

Source: Official DesignArena Website leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Muse Wonder max 1,380
Muse Spark 1.3 xhigh 1,361
Muse Spark 1.3 xhigh, max 1,354
Claude Fable 5.2 1,352
GPT-6 Astra xhigh 1,341
GPT-6 Astra xhigh, max 1,339
Kimi K3 1,337
Inkling 2 Small 1,332
Muse Ember 1,331
Claude Opus 5.5 1,325
Kimi K3.1 Pro 1,323
GPT-5.6 Sol medium, xhigh 1,320
Gemini 4 Argon 1,317
GPT-6.1 Sol 1,315
MiMo-V2.6 Pro 1,312
Muse Spark 1.2 1,311
Claude Sonnet 5.5 1,311
Muse Spark Open xhigh 1,308
Claude Fable 5.1 1,306
GPT-5.6 Sol medium 1,305
Claude Opus 5 1,305
DeepSeek V4.1 Flash 1,299
DeepSeek V4.1 Flash 1017 1,297
Gemini 3.7 Flash 1,296
Gemini 3.6 Flash 1,293
Ling-3.1-flash 1,293
Gemini 4 Carbon 1,293
Gemini 3.8 Flash 1,292
GPT-6 Sol 1,290
Claude Fable 5 1,289
GPT-6.1 Terra 1,287
Claude Opus 4.6 1,284
GLM-5.3 1,280
Claude Opus 4.6 thinking 1,279
Claude Sonnet 4.6 1,278
GLM-5.2 1,278
Grok 4.6 1,278
MiniMax-M3.1-Flash 1,278
Grok 4.5 1,274
Qwen 3.8 Max 1,270
Claude Sonnet 5 1,269
GPT-6 Luna 1,269
Qwen3.7-Max 1,268
Kimi K2.6 1,264
MiMo-V2.5-Pro 1,264
Muse Spark 1.1 1,264
GLM-5.1 1,263
Qwen3.7-Plus 1,262
MiMo-V2.5 1,261
Gemini 3.5 Flash 1,261
GPT-5.6 Terra 1,261
Kimi K2.7 Code 1,259
Mistral Large 4 1,259
GLM-5.3-Flash 1,258
GLM-5-Turbo 1,255
Muse Spark 1,254
Claude Haiku 5.5 1,254
Tencent Hy4 1,253
Claude Opus 4.8 1,251
GPT-5.5 1,249
MiniMax-M3 1,249
GPT-5.6 Luna 1,248
Gemini 3 Pro 1,246
Grok 4.7 1,245
Beam 1.0 max 1,245
Kimi K2.5 thinking 1,242
GLM-5 1,241
Claude Opus 4.5 1,240
MiniMax-M2.7 1,235
Qwen 3.6 Plus 1,235
DeepSeek V4 Flash 0731 1,231
Mercury 3 1,231
DeepSeek-V4-Pro 1,228
Gemini 3.1 Pro 1,227
GLM-5V-Turbo 1,224
Tencent Hy3 1,222
GLM-4.7 1,219
Inkling 1,216
MiniMax-M2.5 1,215
GPT-5.4 medium 1,208
DeepSeek-V4-Flash 1,200
MiniMax-M2.1 1,194
GPT-5.4 none 1,192
GPT-5.4 low 1,191
Gemini 3 Flash 1,189
GPT-5.2 xhigh 1,188
glm-4.7-flash 1,187
Grok 4.3 1,187
Step 3.7 Flash 1,187
Claude 3.7 Sonnet 1,186
Qwen3.5 397B-A17B 1,184
Claude Sonnet 4.5 thinking 1,183
Claude Sonnet 4.5 1,182
DeepSeek-V3.1 thinking 1,180
GPT-5.1 high 1,180
GPT-5 minimal 1,177
GPT-5.2 none 1,177
GPT-5.2 medium 1,177
GPT-5 minimal, high 1,175
Tencent Hy3 low 1,174
DeepSeek-V3.2-Exp 1,172
GPT-5.1 medium 1,171
Claude Opus 4.1 thinking 1,170
GPT-5.2 low 1,170
DeepSeek-V3.2 1,168
GLM-4.6 1,167
GPT-5.1 low 1,165
Solar Pro 4 1,164
GLM-4.5 1,163
Gemini 2.5 Pro Jun 2025 1,160
GPT-5.1 none 1,160
MiMo-V2-Flash 1,160
Nemotron 3.5 Super VL 1,160
Claude Opus 4 1,158
Claude Opus 4.1 1,157
GPT-5.3 Codex 1,156
GPT-5.1-Codex 1,155
Mistral Large 3 1,155
GPT-5.2 high 1,148
DeepSeek-R1 May 2025 1,142
Solar Mini 4 1,141
Claude Sonnet 4 1,139
GLM-4.5-Air 1,139
Mistral Medium 3.5 1,135
Claude Sonnet 4 thinking 1,132
Nemotron 3 Ultra 1,131
Trinity Large Thinking 1,130
Mistral Medium 3.1 1,126
DeepSeek-V3.1 1,115
Claude Haiku 4.5 1,115
DeepSeek-V3 Mar 2025 1,113
Qwen3-Max 1,112
Gemini 2.5 Flash Sep 2025 1,108
Grok 4 Fast 1,107
Kimi K2 Thinking 1,106
GPT-5.1-Codex-mini 1,104
Grok 4.1 Fast 1,098
Grok 4.1 Fast reasoning 1,096
Gemini 2.5 Flash-Lite Sep 2025 1,092
Kimi K2 Sep 2025 1,082
Qwen3-Coder-30B-A3B-Instruct 1,080
Gemini 3.1 Flash-Lite 1,076
Ministral 3 14B 1,074
Gemini 2.5 Flash Sep 2025 1,067
Ministral 3 8B Instruct 1,058
Grok 3 1,052
Grok 4 Fast reasoning 1,048
Qwen3-235B-A22B-Thinking Jul 2025 1,046
Kimi K2 Sep 2025 1,043
GPT-4.1 1,032
o3 1,029
Qwen3-235B-A22B 1,023
Ministral 3 3B Instruct 1,021
Devstral Medium 1,012
Mercury 2 1,011
Grok 4 1,007
GPT-4.1 mini 990
grok-code-fast-1 989
o4-mini 978
Olmo 3.1 32B Think 971
GPT-4.1 nano 966
gpt-oss-120b 961
Qwen3-30B-A3B 948
Grok-3 mini 922
Magistral Small 1.1 905
Mistral Small 3.2 889
Llama 4 Maverick 864
Grok-2 Dec 2024 850
gpt-oss-20b 845
Amazon Nova Premier 828
GPT-4o Mar 2025 824
Devstral Small 1.1 795
Amazon Nova Pro 789
Gemini 1.5 Pro Sep 2024 777
Llama 4 Scout 743

11 models have held number one on the official leaderboard since 2023 11 models have held number one with claims included since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind Amazon xAI Anthropic OpenAI Moonshot AI Meta
Own leaderboard 11 leaders
Muse Wonder 1,380

Source: Official DesignArena Website leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Reported by the lab in its model card
600 800 1,000 1,200 1,400 2025 2026 2027 600 800 1,000 1,200 1,400 2025 2026 2027

Sources: Official DesignArena Website leaderboard and labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Thinking Machines
DateLaunch postScoreAs the post writes it
Nov 5, 2026 Inkling 2 Small 1340 DesignArena Website
Jul 15, 2026 Inkling 1257 DesignArena, agentic web development, 1257 Elo

2 lab claims next to the leaderboard

Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. Every benchmark.

Model Lab says Board says Gap
Inkling 1,257 DesignArena, agentic web development, 1257 Elo 1,216 Leaderboard +41
Inkling 2 Small 1,340 DesignArena Website 1,332 Leaderboard +8

More in Coding

All 282 in Coding
  • SWE-bench Verified In use 500 human-validated GitHub issues from 12 Python repos. Agent writes a patch that must pass hidden tests. Claude Opus 4.7 83.5%
  • LiveCodeBench v6 In use Competitive programming problems collected after model cutoffs from LeetCode, AtCoder, Codeforces. Scored pass@1 on hidden tests. DeepSeek-V4-Pro 93.5%
  • SWE-bench Multilingual In use 300 GitHub-issue tasks across nine programming languages in SWE-bench format. Patch graded by repository tests. Claude Fable 5.2 96.6%
  • DeepSWE In use 113 original long-horizon engineering tasks across 91 repos and five languages, written from scratch. Hand-written verifiers accept alternative solutions. GPT-6 Astra 74.1%
  • SciCode In use Scientist-curated research coding problems split into subproblems across natural sciences. Code checked against test cases. Seed2.1 Pro 59.8%
  • Codeforces rating In use Model solves recent Codeforces contest problems. An Elo-style rating is computed from simulated contest performance. DeepSeek V4.1 Flash 3,471