Skip to content

Benchmark

Design Arena Elo (models/uicomponent)

People compare model answers and choose which they prefer. Higher scores are better.

Models measured
141
Scores recorded
153
Sources
1
IQ weight
1.76

Score distribution

1,148.2
Mean
1,156
Median
140.8
Std dev
945
10th percentile
1,325
90th percentile
752
Min
7521,389
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.76 for chat models, measured over 141 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
51GPT-5.6 Luna· Design Arena Leaderboards data1,232
52MiniMax M3· Design Arena Leaderboards data1,228
53Claude Opus 4.5· Design Arena Leaderboards data1,222
54GPT-5.1 Codex· Design Arena Leaderboards data1,221
55DeepSeek V4 Flash 0731· Design Arena Leaderboards data1,220
56Kimi K2.5· Design Arena Leaderboards data1,220
57Mercury 3· Design Arena Leaderboards data1,219
58Qwen3.6 Plus· Design Arena Leaderboards data1,216
59GLM 5· Design Arena Leaderboards data1,214
60Gemini 3.1 Pro Preview· Design Arena Leaderboards data1,209
61MiniMax M2.1· Design Arena Leaderboards data1,207
62DeepSeek V4 Pro· Design Arena Leaderboards data1,205
63Muse Glimmer 30B· Design Arena Leaderboards data1,201
64GPT 5.4low· Design Arena Leaderboards data1,199
65GLM 5V Turbo· Design Arena Leaderboards data1,195
66GLM 4.7 Flash· Design Arena Leaderboards data1,191
67Grok 4.20· Design Arena Leaderboards data1,184
68GLM 4.7· Design Arena Leaderboards data1,183
69GPT 5.4none· Design Arena Leaderboards data1,183
70Inkling FP4· Design Arena Leaderboards data1,183
71Hy 4· Design Arena Leaderboards data1,182
72Grok 4.3· Design Arena Leaderboards data1,179
73DeepSeek V3.1thinking· Design Arena Leaderboards data1,166
74GPT 5high· Design Arena Leaderboards data1,163
75Qwen3.5 Plus· Design Arena Leaderboards data1,161
76Step 3.7 Flash· Design Arena Leaderboards data1,159
77Claude Sonnet 4.5thinking· Design Arena Leaderboards data1,156
78DeepSeek V3.2 Exp· Design Arena Leaderboards data1,150
79Claude Opus 4.1thinking, 20250805· Design Arena Leaderboards data1,148
80DeepSeek V4 Flash· Design Arena Leaderboards data1,148
81v0-1.5-lg· Design Arena Leaderboards data1,148
82Hy3 (Deep Infra)· Design Arena Leaderboards data1,147
83Qwen3.5 397B A17B· Design Arena Leaderboards data1,147
84Nemotron 3.5 Super VL· Design Arena Leaderboards data1,146
85Claude Sonnet 4.5· Design Arena Leaderboards data1,145
86GPT 5.1high· Design Arena Leaderboards data1,141
87Claude Opus 4.1· Design Arena Leaderboards data1,139
88GPT 5.1low· Design Arena Leaderboards data1,138
89Claude Opus 4· Design Arena Leaderboards data1,137
90Claude Sonnet 3.7· Design Arena Leaderboards data1,135
91DeepSeek V3.2· Design Arena Leaderboards data1,133
92GLM 4.6· Design Arena Leaderboards data1,131
93GPT 5· Design Arena Leaderboards data1,129
94GLM 4.5· Design Arena Leaderboards data1,128
95MiMo V2 Flash· Design Arena Leaderboards data1,128
96GPT 5.1none· Design Arena Leaderboards data1,127
97Gemini 2.5 Pro· Design Arena Leaderboards data1,123
98GPT-5.3 Codex· Design Arena Leaderboards data1,121
99Nemotron 3 Ultra· Design Arena Leaderboards data1,120
100Claude Sonnet 4· Design Arena Leaderboards data1,112

Showing 51–100 of 153 results.