Skip to content

Benchmark

Design Arena Elo (models/3d)

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

Models measured
135
Scores recorded
147
Sources
1
IQ weight
1.86

Score distribution

1,135.7
Mean
1,115
Median
150.4
Std dev
965
10th percentile
1,341
90th percentile
804
Min
8041,492
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.86 for chat models, measured over 135 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101Mistral Medium 3.1· Design Arena Leaderboards data1,048
102Trinity Large Thinking· Design Arena Leaderboards data1,048
103DeepSeek V3.1· Design Arena Leaderboards data1,044
104Qwen3 Max· Design Arena Leaderboards data1,041
105Claude Haiku 4.5· Design Arena Leaderboards data1,039
106gemini-2.5-flash-preview-09-2025· Design Arena Leaderboards data1,038
107GPT 5.4low· Design Arena Leaderboards data1,032
108Grok Code Fast 1· Design Arena Leaderboards data1,032
109Grok 4.1 Fastnon-reasoning· Design Arena Leaderboards data1,029
110GPT 5.1high· Design Arena Leaderboards data1,028
111Mistral Medium 3.5· Design Arena Leaderboards data1,028
112GPT 5· Design Arena Leaderboards data1,023
113Grok 4 Fastnon-reasoning· Design Arena Leaderboards data1,023
114Grok 4· Design Arena Leaderboards data1,018
115Grok 4 Fastreasoning· Design Arena Leaderboards data1,018
116GPT 5.1none· Design Arena Leaderboards data1,017
117Grok 3· Design Arena Leaderboards data1,017
118Gemini 3.1 Flash Lite· Design Arena Leaderboards data1,015
119GPT 5.4none· Design Arena Leaderboards data1,014
120GPT 5.1low· Design Arena Leaderboards data1,010
121GPT-5 mini· Design Arena Leaderboards data1,004
122Magistral Medium· Design Arena Leaderboards data1,001
123Devstral Medium· Design Arena Leaderboards data1,000
124Ministral 8B2512· Design Arena Leaderboards data999
125GPT 5high· Design Arena Leaderboards data993
126Grok 4.1 Fastreasoning· Design Arena Leaderboards data989
127Gemini 2.5 Flash· Design Arena Leaderboards data988
128Codestral 25.012508· Design Arena Leaderboards data987
129GPT-5.3 Codex· Design Arena Leaderboards data975
130Magistral Small 2509· Design Arena Leaderboards data974
131Olmo 3.1 32B Think· Design Arena Leaderboards data970
132Qwen 3 235B A22B Thinking 2507· Design Arena Leaderboards data965
133Qwen3 235B A22B Instruct 2507· Design Arena Leaderboards data961
134Ministral 14B2512· Design Arena Leaderboards data957
135GPT-5.1 Codex Mini· Design Arena Leaderboards data955
136Mercury 2· Design Arena Leaderboards data940
137Gemini 2.5 Flash Lite Preview 09-2025· Design Arena Leaderboards data933
138GPT-5 nano· Design Arena Leaderboards data933
139Ministral 3B2512· Design Arena Leaderboards data930
140Grok 3 Mini· Design Arena Leaderboards data922
141GPT-4.1 nano· Design Arena Leaderboards data892
142GPT OSS 120B· Design Arena Leaderboards data869
143Llama 4 Maverick· Design Arena Leaderboards data868
144GPT 4o· Design Arena Leaderboards data836
145Qwen 3 235B A22B· Design Arena Leaderboards data826
146GPT 4.1· Design Arena Leaderboards data817
147GPT-4.1 mini· Design Arena Leaderboards data804

Showing 101–147 of 147 results.