Design Arena Website Elo
A display-only Design Arena website-generation Elo score surfaced on OpenRouter model benchmark pages.
91 models
Higher is better.
- 1Muse WonderMeta1360
- 2Muse Spark 1.3Meta1356
- 3Kimi K3Moonshot AI1336
- 4Claude Opus 5.5Anthropic1335
- 5Claude Sonnet 5.5Anthropic1324
- 6DeepSeek V4.1 Flash 1017DeepSeek1323
- 7GPT-6.1 SolOpenAI1321
- 8Gemini 4 ArgonGoogle1315
- 9Claude Fable 5.1Anthropic1314
- 10Muse Spark 1.2Meta1313
- 11Claude Opus 5Anthropic1309
- 12MiMo-V2.6-ProXiaomi1308
- 13Gemini 3.7 FlashGoogle1304
- 14Gemini 3.8 FlashGoogle1300
- 15Gemini 3.6 FlashGoogle1300
- 16Claude Fable 5Anthropic1297
- 17GLM-5.3Z.AI1295
- 18Claude Opus 4.6Anthropic1291
- 19GLM-5.1Z.AI1290
- 20Grok 4.6xAI1289
- 21Claude Sonnet 4.6Anthropic1286
- 22GLM-5.2Z.AI1285
- 23Grok 4.5xAI1281
- 24Claude Sonnet 5Anthropic1274
- 25Qwen3.7 MaxAlibaba1274
- 26GLM-5.3-FlashZ.AI1272
- 27Muse Spark 1.1Meta1270
- 28Qwen3.7 PlusAlibaba1270
- 29Kimi K2.6Moonshot AI1269
- 30Gemini 3.5 FlashGoogle1268
- 31MiMo-V2.5-ProXiaomi1267
- 32MiMo-V2.5Xiaomi1266
- 33Kimi K2.7 CodeMoonshot AI1265
- 34Claude Haiku 5.5Anthropic1263
- 35GLM-5-TurboZ.AI1262
- 36Mistral Large 4Mistral1259
- 37Claude Opus 4.8Anthropic1258
- 38DeepSeek V4 Pro 0813DeepSeek1258
- 39MiniMax M3MiniMax1258
- 40GPT-5.5OpenAI1257
About this benchmark
- Metric
- Elo
- Tasks
- Website generation comparisons
- Authors
- Design Arena (2026)
Scores are as reported by model developers or evaluators and may use different settings (for example reasoning effort or tools). Compare with care.
All results
| 1 | Muse Wonder Meta | 1360 |
| 2 | Muse Spark 1.3 Meta | 1356 |
| 3 | Kimi K3 Moonshot AI | 1336 |
| 4 | Claude Opus 5.5 Anthropic | 1335 |
| 5 | Claude Sonnet 5.5 Anthropic | 1324 |
| 6 | DeepSeek V4.1 Flash 1017 DeepSeek | 1323 |
| 7 | GPT-6.1 Sol OpenAI | 1321 |
| 8 | Gemini 4 Argon Google | 1315 |
| 9 | Claude Fable 5.1 Anthropic | 1314 |
| 10 | Muse Spark 1.2 Meta | 1313 |
| 11 | Claude Opus 5 Anthropic | 1309 |
| 12 | MiMo-V2.6-Pro Xiaomi | 1308 |
| 13 | Gemini 3.7 Flash Google | 1304 |
| 14 | Gemini 3.8 Flash Google | 1300 |
| 15 | Gemini 3.6 Flash Google | 1300 |
| 16 | Claude Fable 5 Anthropic | 1297 |
| 17 | GLM-5.3 Z.AI | 1295 |
| 18 | Claude Opus 4.6 Anthropic | 1291 |
| 19 | GLM-5.1 Z.AI | 1290 |
| 20 | Grok 4.6 xAI | 1289 |
| 21 | Claude Sonnet 4.6 Anthropic | 1286 |
| 22 | GLM-5.2 Z.AI | 1285 |
| 23 | Grok 4.5 xAI | 1281 |
| 24 | Claude Sonnet 5 Anthropic | 1274 |
| 25 | Qwen3.7 Max Alibaba | 1274 |
| 26 | GLM-5.3-Flash Z.AI | 1272 |
| 27 | Muse Spark 1.1 Meta | 1270 |
| 28 | Qwen3.7 Plus Alibaba | 1270 |
| 29 | Kimi K2.6 Moonshot AI | 1269 |
| 30 | Gemini 3.5 Flash Google | 1268 |
| 31 | MiMo-V2.5-Pro Xiaomi | 1267 |
| 32 | MiMo-V2.5 Xiaomi | 1266 |
| 33 | Kimi K2.7 Code Moonshot AI | 1265 |
| 34 | Claude Haiku 5.5 Anthropic | 1263 |
| 35 | GLM-5-Turbo Z.AI | 1262 |
| 36 | Mistral Large 4 Mistral | 1259 |
| 37 | Claude Opus 4.8 Anthropic | 1258 |
| 38 | DeepSeek V4 Pro 0813 DeepSeek | 1258 |
| 39 | MiniMax M3 MiniMax | 1258 |
| 40 | GPT-5.5 OpenAI | 1257 |
| 41 | Gemini 3.1 Pro Google | 1254 |
| 42 | Grok 4.7 xAI | 1251 |
| 43 | Kimi K2.5 (Reasoning) Moonshot AI | 1249 |
| 44 | Kimi K2.5 Moonshot AI | 1249 |
| 45 | Claude Opus 4.5 Thinking Anthropic | 1248 |
| 46 | Claude Opus 4.5 Anthropic | 1248 |
| 47 | GLM-5 Z.AI | 1247 |
| 48 | Qwen3.6 Plus Alibaba | 1243 |
| 49 | MiniMax M2.7 MiniMax | 1243 |
| 50 | Grok 4.20 xAI | 1231 |
| 51 | GLM-5V-Turbo Z.AI | 1230 |
| 52 | GLM-4.7 Z.AI | 1227 |
| 53 | Inkling Thinking Machines Lab | 1224 |
| 54 | GPT-5.4 OpenAI | 1221 |
| 55 | DeepSeek V4 Flash 0731 DeepSeek | 1208 |
| 56 | GPT-5.2 OpenAI | 1196 |
| 57 | Gemini 3 Flash Google | 1196 |
| 58 | Grok 4.3 xAI | 1196 |
| 59 | Step 3.7 Flash StepFun | 1196 |
| 60 | Claude Sonnet 4.5 Anthropic | 1191 |
| 61 | GPT-5.1 OpenAI | 1188 |
| 62 | GPT-5 (medium) OpenAI | 1186 |
| 63 | GPT-5 (high) OpenAI | 1186 |
| 64 | Hy3 Tencent | 1183 |
| 65 | Claude 4.1 Opus Anthropic | 1178 |
| 66 | Solar Pro 4 Upstage | 1177 |
| 67 | DeepSeek V3.2 DeepSeek | 1176 |
| 68 | GLM-4.5 Z.AI | 1171 |
| 69 | Gemini 2.5 Pro Google | 1167 |
| 70 | GPT-5.3 Codex OpenAI | 1164 |
| 71 | GPT-5.1-Codex OpenAI | 1163 |
| 72 | Qwen3-Coder 480B-A35B Alibaba | 1160 |
| 73 | GLM-4.5-Air Z.AI | 1148 |
| 74 | Nemotron 3 Ultra NVIDIA | 1145 |
| 75 | Trinity-Large-Thinking Arcee AI | 1137 |
| 76 | DeepSeek V3.1 DeepSeek | 1124 |
| 77 | DeepSeek V3.1 (Reasoning) DeepSeek | 1124 |
| 78 | Claude Haiku 4.5 Anthropic | 1122 |
| 79 | DeepSeek V3 DeepSeek | 1120 |
| 80 | Gemini 2.5 Flash Google | 1115 |
| 81 | Mistral Medium 3 Mistral | 1080 |
| 82 | Kimi K2 Moonshot AI | 1050 |
| 83 | GPT-4.1 OpenAI | 1040 |
| 84 | o3 OpenAI | 1036 |
| 85 | GPT-4.1 mini OpenAI | 997 |
| 86 | GPT-4.1 nano OpenAI | 974 |
| 87 | GPT-OSS 120B OpenAI | 969 |
| 88 | Llama 4 Maverick Meta | 871 |
| 89 | GPT-OSS 20B OpenAI | 854 |
| 90 | GPT-4o OpenAI | 831 |
| 91 | Llama 4 Scout Meta | 750 |