Skip to content

Benchmark

Design Arena Elo (models/gamedev)

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

Models measured
148
Scores recorded
160
Sources
1
IQ weight
1.91

Score distribution

1,136.4
Mean
1,134
Median
150.8
Std dev
942
10th percentile
1,317
90th percentile
745
Min
7451,540
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.91 for chat models, measured over 148 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
101GPT-5 mini· Design Arena Leaderboards data1,101
102v0-1.5-lg· Design Arena Leaderboards data1,100
103Muse Glimmer 30B· Design Arena Leaderboards data1,086
104Gemini 2.5 Pro· Design Arena Leaderboards data1,083
105Qwen3.5 Plus· Design Arena Leaderboards data1,078
106Qwen3 Coder· Design Arena Leaderboards data1,071
107Solar Mini 4· Design Arena Leaderboards data1,070
108Claude Haiku 4.5· Design Arena Leaderboards data1,069
109Nemotron 3.5 Super VL· Design Arena Leaderboards data1,067
110Qwen3 Max· Design Arena Leaderboards data1,067
111GLM 4.5 Air· Design Arena Leaderboards data1,066
112GPT-5.1 Codex Mini· Design Arena Leaderboards data1,064
113Kimi K2 Turbo Preview· Design Arena Leaderboards data1,057
114DeepSeek V3.1· Design Arena Leaderboards data1,056
115GPT 4.1· Design Arena Leaderboards data1,052
116Mistral Large 3· Design Arena Leaderboards data1,052
117Mistral Medium 3.5· Design Arena Leaderboards data1,051
118Trinity Large Thinking· Design Arena Leaderboards data1,051
119INTELLECT-3· Design Arena Leaderboards data1,049
120Mistral Medium 3.1· Design Arena Leaderboards data1,046
121GPT-4.1 mini· Design Arena Leaderboards data1,043
122Grok 4.1 Fastnon-reasoning· Design Arena Leaderboards data1,039
123gemini-2.5-flash-preview-09-2025· Design Arena Leaderboards data1,038
124Grok 4 Fastnon-reasoning· Design Arena Leaderboards data1,038
125Grok 4.1 Fastreasoning· Design Arena Leaderboards data1,032
126DeepSeek Chat· Design Arena Leaderboards data1,025
127Gemini 2.5 Flash Lite Preview 09-2025· Design Arena Leaderboards data1,019
128GPT-5 nano· Design Arena Leaderboards data1,017
129Ministral 14B2512· Design Arena Leaderboards data1,010
130Gemini 3.1 Flash Lite· Design Arena Leaderboards data1,002
131Grok 3· Design Arena Leaderboards data998
132v0-1.5-md· Design Arena Leaderboards data995
133Grok 4 Fastreasoning· Design Arena Leaderboards data994
134Mistral Medium 3· Design Arena Leaderboards data990
135Gemini 2.5 Flash· Design Arena Leaderboards data977
136Grok 4· Design Arena Leaderboards data974
137Magistral Medium· Design Arena Leaderboards data968
138GPT OSS 120B· Design Arena Leaderboards data964
139Ministral 8B2512· Design Arena Leaderboards data962
140Grok Code Fast 1· Design Arena Leaderboards data960
141Devstral Medium· Design Arena Leaderboards data958
142kimi-k2-0711-preview· Design Arena Leaderboards data946
143Mercury 2· Design Arena Leaderboards data944
144GPT-4.1 nano· Design Arena Leaderboards data942
145Codestral 25.012508· Design Arena Leaderboards data940
146Olmo 3.1 32B Think· Design Arena Leaderboards data938
147Qwen 3 235B A22B Thinking 2507· Design Arena Leaderboards data929
148Qwen3 235B A22B Instruct 2507· Design Arena Leaderboards data923
149Grok 3 Mini· Design Arena Leaderboards data922
150Ministral 3B2512· Design Arena Leaderboards data920

Showing 101–150 of 160 results.