Skip to content

Design Arena Website Elo

A display-only Design Arena website-generation Elo score surfaced on OpenRouter model benchmark pages.

91 models

Higher is better.

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

1Muse Wonder Meta1360
2Muse Spark 1.3 Meta1356
3Kimi K3 Moonshot AI1336
4Claude Opus 5.5 Anthropic1335
5Claude Sonnet 5.5 Anthropic1324
6DeepSeek V4.1 Flash 1017 DeepSeek1323
7GPT-6.1 Sol OpenAI1321
8Gemini 4 Argon Google1315
9Claude Fable 5.1 Anthropic1314
10Muse Spark 1.2 Meta1313
11Claude Opus 5 Anthropic1309
12MiMo-V2.6-Pro Xiaomi1308
13Gemini 3.7 Flash Google1304
14Gemini 3.8 Flash Google1300
15Gemini 3.6 Flash Google1300
16Claude Fable 5 Anthropic1297
17GLM-5.3 Z.AI1295
18Claude Opus 4.6 Anthropic1291
19GLM-5.1 Z.AI1290
20Grok 4.6 xAI1289
21Claude Sonnet 4.6 Anthropic1286
22GLM-5.2 Z.AI1285
23Grok 4.5 xAI1281
24Claude Sonnet 5 Anthropic1274
25Qwen3.7 Max Alibaba1274
26GLM-5.3-Flash Z.AI1272
27Muse Spark 1.1 Meta1270
28Qwen3.7 Plus Alibaba1270
29Kimi K2.6 Moonshot AI1269
30Gemini 3.5 Flash Google1268
31MiMo-V2.5-Pro Xiaomi1267
32MiMo-V2.5 Xiaomi1266
33Kimi K2.7 Code Moonshot AI1265
34Claude Haiku 5.5 Anthropic1263
35GLM-5-Turbo Z.AI1262
36Mistral Large 4 Mistral1259
37Claude Opus 4.8 Anthropic1258
38DeepSeek V4 Pro 0813 DeepSeek1258
39MiniMax M3 MiniMax1258
40GPT-5.5 OpenAI1257
41Gemini 3.1 Pro Google1254
42Grok 4.7 xAI1251
43Kimi K2.5 (Reasoning) Moonshot AI1249
44Kimi K2.5 Moonshot AI1249
45Claude Opus 4.5 Thinking Anthropic1248
46Claude Opus 4.5 Anthropic1248
47GLM-5 Z.AI1247
48Qwen3.6 Plus Alibaba1243
49MiniMax M2.7 MiniMax1243
50Grok 4.20 xAI1231
51GLM-5V-Turbo Z.AI1230
52GLM-4.7 Z.AI1227
53Inkling Thinking Machines Lab1224
54GPT-5.4 OpenAI1221
55DeepSeek V4 Flash 0731 DeepSeek1208
56GPT-5.2 OpenAI1196
57Gemini 3 Flash Google1196
58Grok 4.3 xAI1196
59Step 3.7 Flash StepFun1196
60Claude Sonnet 4.5 Anthropic1191
61GPT-5.1 OpenAI1188
62GPT-5 (medium) OpenAI1186
63GPT-5 (high) OpenAI1186
64Hy3 Tencent1183
65Claude 4.1 Opus Anthropic1178
66Solar Pro 4 Upstage1177
67DeepSeek V3.2 DeepSeek1176
68GLM-4.5 Z.AI1171
69Gemini 2.5 Pro Google1167
70GPT-5.3 Codex OpenAI1164
71GPT-5.1-Codex OpenAI1163
72Qwen3-Coder 480B-A35B Alibaba1160
73GLM-4.5-Air Z.AI1148
74Nemotron 3 Ultra NVIDIA1145
75Trinity-Large-Thinking Arcee AI1137
76DeepSeek V3.1 DeepSeek1124
77DeepSeek V3.1 (Reasoning) DeepSeek1124
78Claude Haiku 4.5 Anthropic1122
79DeepSeek V3 DeepSeek1120
80Gemini 2.5 Flash Google1115
81Mistral Medium 3 Mistral1080
82Kimi K2 Moonshot AI1050
83GPT-4.1 OpenAI1040
84o3 OpenAI1036
85GPT-4.1 mini OpenAI997
86GPT-4.1 nano OpenAI974
87GPT-OSS 120B OpenAI969
88Llama 4 Maverick Meta871
89GPT-OSS 20B OpenAI854
90GPT-4o OpenAI831
91Llama 4 Scout Meta750