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
1Claude Fable 5.2· Design Arena Leaderboards data1,492
2Gemini 4 Neon· Design Arena Leaderboards data1,489
3GPT-6.2 Sol· Design Arena Leaderboards data1,477
4Claude Opus 5.5· Design Arena Leaderboards data1,450
5GPT-6 Astra· Design Arena Leaderboards data1,450
6GPT-6.2 Astra· Design Arena Leaderboards data1,430
7Kimi K3.1 Pro· Design Arena Leaderboards data1,430
8Muse Wonder 1.0· Design Arena Leaderboards data1,420
9GPT-6.1 Sol· Design Arena Leaderboards data1,414
10Gemini 4 Carbon· Design Arena Leaderboards data1,413
11Gemini 4 Hydrogen· Design Arena Leaderboards data1,396
12Claude Sonnet 5.5· Design Arena Leaderboards data1,393
13Claude Fable 5.1· Design Arena Leaderboards data1,375
14GPT-5.6 Solxhigh· Design Arena Leaderboards data1,355
15Kimi K3· Design Arena Leaderboards data1,352
16Gemini 4 Argon· Design Arena Leaderboards data1,341
17Muse Spark 1.3· Design Arena Leaderboards data1,335
18DeepSeek V4.1 Flash 1017· Design Arena Leaderboards data1,330
19DeepSeek V4.1 Flash· Design Arena Leaderboards data1,325
20Claude Opus 5· Design Arena Leaderboards data1,309
21Claude Haiku 5.5· Design Arena Leaderboards data1,307
22Qwen3.8 Max Preview· Design Arena Leaderboards data1,306
23GPT-6 Sol· Design Arena Leaderboards data1,288
24GPT-6.1 Terra· Design Arena Leaderboards data1,288
25Claude Fable 5· Design Arena Leaderboards data1,284
26GPT-5.6 Sol· Design Arena Leaderboards data1,280
27Gemini 3.7 Flash· Design Arena Leaderboards data1,274
28Muse Spark 1.2· Design Arena Leaderboards data1,270
29Gemini 3.8 Flash· Design Arena Leaderboards data1,262
30GLM 5.2· Design Arena Leaderboards data1,253
31Claude Opus 4.6· Design Arena Leaderboards data1,241
32Grok 4.7· Design Arena Leaderboards data1,241
33Claude Opus 4.6thinking· Design Arena Leaderboards data1,238
34Gemini 3.6 Flash· Design Arena Leaderboards data1,237
35Hy 4· Design Arena Leaderboards data1,236
36Kimi K2.6· Design Arena Leaderboards data1,235
37Qwen3.7 Max· Design Arena Leaderboards data1,231
38Claude Sonnet 5· Design Arena Leaderboards data1,225
39Mistral Large 4· Design Arena Leaderboards data1,225
40Muse Spark Open· Design Arena Leaderboards data1,225
41MiMo V2.5 Pro· Design Arena Leaderboards data1,221
42DeepSeek V4 Pro· Design Arena Leaderboards data1,220
43GLM 5 Turbo· Design Arena Leaderboards data1,214
44Hy4 Flash· Design Arena Leaderboards data1,213
45Gemini 3.5 Flash· Design Arena Leaderboards data1,212
46Kimi K2.7 Code· Design Arena Leaderboards data1,207
47Mercury 3· Design Arena Leaderboards data1,205
48Qwen3.7 Plus· Design Arena Leaderboards data1,205
49Claude Sonnet 4.6· Design Arena Leaderboards data1,201
50Gemini 3.1 Pro Preview· Design Arena Leaderboards data1,201

Showing 1–50 of 147 results.