Skip to content

Benchmark

Design Arena Elo (models/svg)

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

Models measured
100
Scores recorded
112
Sources
1
IQ weight
1.97

Score distribution

1,139.3
Mean
1,140
Median
115.3
Std dev
977
10th percentile
1,288
90th percentile
856
Min
8561,413
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 1.97 for chat models, measured over 98 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.

Leaderboard

#ModelScore
1GPT-6 Astra· Design Arena Leaderboards data1,413
2Gemini 4 Carbon· Design Arena Leaderboards data1,395
3Gemini 4 Argon· Design Arena Leaderboards data1,334
4GPT-6.1 Sol· Design Arena Leaderboards data1,333
5Kimi K3.1 Pro· Design Arena Leaderboards data1,319
6Claude Opus 5.5· Design Arena Leaderboards data1,315
7Claude Opus 5· Design Arena Leaderboards data1,298
8GPT-5.6 Solxhigh· Design Arena Leaderboards data1,298
9GPT-6.1 Terra· Design Arena Leaderboards data1,297
10GPT-6 Sol· Design Arena Leaderboards data1,296
11Kimi K3· Design Arena Leaderboards data1,292
12Claude Sonnet 5.5· Design Arena Leaderboards data1,288
13Claude Fable 5· Design Arena Leaderboards data1,287
14Claude Fable 5.1· Design Arena Leaderboards data1,287
15GPT-5.6 Sol· Design Arena Leaderboards data1,287
16Muse Spark 1.3· Design Arena Leaderboards data1,287
17Muse Wonder 1.0· Design Arena Leaderboards data1,286
18Gemini 3.8 Flash· Design Arena Leaderboards data1,283
19Gemini 3.7 Flash· Design Arena Leaderboards data1,271
20Gemini 3.1 Pro Preview· Design Arena Leaderboards data1,270
21Muse Spark 1.2· Design Arena Leaderboards data1,264
22Arrow 1.1 Max· Design Arena Leaderboards data1,259
23Grok 4.7· Design Arena Leaderboards data1,258
24Prism· Design Arena Leaderboards data1,258
25Gemini 3.5 Flash· Design Arena Leaderboards data1,241
26DeepSeek V4.1 Flash 1017· Design Arena Leaderboards data1,238
27GPT-6 Luna· Design Arena Leaderboards data1,230
28DeepSeek V4.1 Flash· Design Arena Leaderboards data1,225
29GPT 5.5· Design Arena Leaderboards data1,219
30Mistral Large 4· Design Arena Leaderboards data1,216
31Claude Opus 4.6thinking· Design Arena Leaderboards data1,212
32GPT-5.6 Terra· Design Arena Leaderboards data1,203
33Qwen3.7 Max· Design Arena Leaderboards data1,201
34Claude Haiku 5.5· Design Arena Leaderboards data1,200
35Claude Opus 4.6· Design Arena Leaderboards data1,199
36Qwen3.7 Plus· Design Arena Leaderboards data1,194
37Arrow 1.1· Design Arena Leaderboards data1,190
38GLM 5 Turbo· Design Arena Leaderboards data1,189
39GLM 5.2· Design Arena Leaderboards data1,189
40Claude Sonnet 4.6· Design Arena Leaderboards data1,181
41MiMo V2.5 Pro· Design Arena Leaderboards data1,180
42Claude Sonnet 5· Design Arena Leaderboards data1,178
43Claude Opus 4.8· Design Arena Leaderboards data1,176
44GPT-5.6 Luna· Design Arena Leaderboards data1,176
45GPT 5high· Design Arena Leaderboards data1,173
46MiMo V2.5· Design Arena Leaderboards data1,173
47Claude Opus 4.5· Design Arena Leaderboards data1,165
48Kimi K2.6· Design Arena Leaderboards data1,165
49DeepSeek V4 Flash 0731· Design Arena Leaderboards data1,164
50Mercury 3· Design Arena Leaderboards data1,160

Showing 1–50 of 112 results.