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
101Claude Sonnet 4thinking· Design Arena Leaderboards data1,109
102GLM 4.5 Air· Design Arena Leaderboards data1,107
103Qwen3 Coder· Design Arena Leaderboards data1,096
104GPT-5 mini· Design Arena Leaderboards data1,090
105Mistral Large 3· Design Arena Leaderboards data1,085
106Claude Haiku 4.5· Design Arena Leaderboards data1,084
107Solar Mini 4· Design Arena Leaderboards data1,084
108Mistral Medium 3.1· Design Arena Leaderboards data1,083
109DeepSeek Chat· Design Arena Leaderboards data1,077
110gemini-2.5-flash-preview-09-2025· Design Arena Leaderboards data1,077
111DeepSeek V3.1· Design Arena Leaderboards data1,069
112GPT-5.1 Codex Mini· Design Arena Leaderboards data1,065
113Mistral Medium 3.5· Design Arena Leaderboards data1,063
114Qwen3 Max· Design Arena Leaderboards data1,062
115INTELLECT-3· Design Arena Leaderboards data1,061
116Grok 4 Fastnon-reasoning· Design Arena Leaderboards data1,056
117Gemini 3.1 Flash Lite· Design Arena Leaderboards data1,055
118GPT-5 nano· Design Arena Leaderboards data1,050
119Grok 4.1 Fastreasoning· Design Arena Leaderboards data1,037
120Qwen3 Coder 30B A3B Instruct· Design Arena Leaderboards data1,030
121Trinity Large Thinking· Design Arena Leaderboards data1,029
122Grok 4.1 Fastnon-reasoning· Design Arena Leaderboards data1,021
123Grok 3· Design Arena Leaderboards data1,020
124kimi-k2-0711-preview· Design Arena Leaderboards data1,014
125Grok 4 Fastreasoning· Design Arena Leaderboards data1,011
126Gemini 2.5 Flash Lite Preview 09-2025· Design Arena Leaderboards data1,009
127Mistral Medium 3· Design Arena Leaderboards data1,008
128Magistral Medium· Design Arena Leaderboards data1,007
129Codestral 25.012508· Design Arena Leaderboards data1,001
130v0-1.5-md· Design Arena Leaderboards data993
131Gemini 2.5 Flash· Design Arena Leaderboards data989
132GPT 4.1· Design Arena Leaderboards data984
133Grok Code Fast 1· Design Arena Leaderboards data974
134Grok 4· Design Arena Leaderboards data970
135Devstral Medium· Design Arena Leaderboards data963
136Mercury 2· Design Arena Leaderboards data963
137Qwen3 235B A22B Instruct 2507· Design Arena Leaderboards data949
138GPT-4.1 mini· Design Arena Leaderboards data945
139Qwen 3 235B A22B· Design Arena Leaderboards data943
140Qwen 3 235B A22B Thinking 2507· Design Arena Leaderboards data929
141Qwen3 30B A3B· Design Arena Leaderboards data929
142Magistral Small 2509· Design Arena Leaderboards data914
143GPT OSS 120B· Design Arena Leaderboards data911
144GPT-4.1 nano· Design Arena Leaderboards data900
145Mistral Small2506· Design Arena Leaderboards data891
146Llama 4 Maverick· Design Arena Leaderboards data883
147Grok 3 Mini· Design Arena Leaderboards data874
148GPT 4o· Design Arena Leaderboards data869
149Olmo 3.1 32B Think· Design Arena Leaderboards data842
150Codestral 2· Design Arena Leaderboards data836

Showing 101–150 of 153 results.