Skip to content

Benchmark

Design Arena Elo (models/image)

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

Models measured
58
Scores recorded
59
Sources
1
IQ weight
0.98

Score distribution

1,159.6
Mean
1,159
Median
95.2
Std dev
1,038
10th percentile
1,283
90th percentile
986
Min
9861,383
The band covers the middle 80% of scores. The line marks the median.

This benchmark has a weight of 0.98 for image-generation models, measured over 55 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-Image-2.5 Sunburst· Design Arena Leaderboards data1,383
2GPT-Image-2.5 Flare· Design Arena Leaderboards data1,355
3GPT Image 2· Design Arena Leaderboards data1,338
4MAI Image 2.7· Design Arena Leaderboards data1,336
5MAI Image 2.7 Flash· Design Arena Leaderboards data1,312
6MAI-Image-2.6· Design Arena Leaderboards data1,296
7MAI-Image-2.6-Flash· Design Arena Leaderboards data1,283
8Nano Banana 2.1· Design Arena Leaderboards data1,279
9Grok Imagine Image 2.0auto· Design Arena Leaderboards data1,271
10Seedream 5.5· Design Arena Leaderboards data1,257
11Qwen Image 3.0 Pro· Design Arena Leaderboards data1,248
12Gemini 3.1 Flash Image· Design Arena Leaderboards data1,244
13FLUX 3 Image· Design Arena Leaderboards data1,243
14Muse Image 1.0· Design Arena Leaderboards data1,243
15Seedream 5.0 Pro· Design Arena Leaderboards data1,241
16Gemini 3.1 Flash-Lite Image· Design Arena Leaderboards data1,215
17Mai Image 2.5· Design Arena Leaderboards data1,210
18MiniMax H3-Image· Design Arena Leaderboards data1,201
19UNI-1.1 Max· Design Arena Leaderboards data1,200
20Gemini 3 Pro Image· Design Arena Leaderboards data1,192
21UNI-1.1· Design Arena Leaderboards data1,190
22Krea v2 Medium· Design Arena Leaderboards data1,188
23Krea 2 Turbo· Design Arena Leaderboards data1,186
24Krea v2 Large· Design Arena Leaderboards data1,184
25FLUX.2 [flex]· Design Arena Leaderboards data1,175
26FLUX.2 [pro]· Design Arena Leaderboards data1,171
27GPT Image 1· Design Arena Leaderboards data1,167
28Gemini 2.5 Flash Image· Design Arena Leaderboards data1,161
29Imagen 4 Ultra· Design Arena Leaderboards data1,161
30GPT-Image-1 mini· Design Arena Leaderboards data1,159
31Doubao Seedream 4-0· Design Arena Leaderboards data1,158
32Ideogram 4.6 Text to Imagehigh· Design Arena Leaderboards data1,155
33FLUX 3 Image Klein· Design Arena Leaderboards data1,151
34Wan 2.7 Pro· Design Arena Leaderboards data1,144
35Imagen 4· Design Arena Leaderboards data1,143
36Wan 2.7· Design Arena Leaderboards data1,134
37Imagen 3· Design Arena Leaderboards data1,132
38Flux Kontext Max· Design Arena Leaderboards data1,130
39Hunyuan Image V3· Design Arena Leaderboards data1,106
40FLUX.2 [dev]· Design Arena Leaderboards data1,105
41Qwen Image2512· Design Arena Leaderboards data1,099
42Boogu Image· Design Arena Leaderboards data1,092
43Flux Kontext Pro· Design Arena Leaderboards data1,090
44FLUX.2 [klein] 9B· Design Arena Leaderboards data1,086
45GLM-Image· Design Arena Leaderboards data1,076
46Z Image Turbo· Design Arena Leaderboards data1,075
47Ideogram 3.0· Design Arena Leaderboards data1,069
48ERNIE Image Turbo· Design Arena Leaderboards data1,063
49ERNIE Image· Design Arena Leaderboards data1,059
50FLUX 1.1 Pro Ultra· Design Arena Leaderboards data1,051

Showing 1–50 of 59 results.