llm.ing

Design Arena — fullstack

mirrorrun by Design Arenaunit: elo46 modelssource ↗

Caveat: Head-to-head human votes on generated designs/code, mirrored via OpenRouter.

websitecodecategoriesgamedev3duicomponentdatavizsvgasciiartmobileappswebapps+19 more
#ModelScoreObserved
1Claude Opus 4.7
1503
Jul 23, 2026
2Claude Fable 5.2
1402
Nov 19, 2026
3Claude Opus 5.5
1383
Nov 19, 2026
4Qwen3.8 Max
1332
Sep 4, 2026
5Kimi K3.1 Pro
1322
Nov 19, 2026
6Claude Fable 5.1
1297
Nov 19, 2026
7Kimi K3
1285
Nov 19, 2026
8Muse Spark 1.3
1284
Nov 19, 2026
9Claude Opus 5
1279
Nov 19, 2026
10Claude Fable 5
1251
Nov 19, 2026
11Grok 4.6
1234
Nov 19, 2026
12Claude Opus 4.8
1221
Nov 19, 2026
12Claude Sonnet 5
1221
Nov 19, 2026
14Grok 4.5
1219
Nov 19, 2026
15Gemini 3.8 Flash
1212
Nov 19, 2026
16GLM-5.2
1211
Nov 19, 2026
17Claude Opus 4.6
1190
Nov 19, 2026
18Claude Sonnet 4.6
1183
Nov 19, 2026
19Muse Spark 1.2
1180
Nov 19, 2026
20Gemini 3.7 Flash
1178
Nov 19, 2026
21MiniMax-M3
1172
Nov 19, 2026
22Gemini 3.5 Flash
1167
Nov 19, 2026
22Muse Spark 1.1
1167
Nov 19, 2026
24Qwen3.7 Max
1163
Nov 19, 2026
25Gemini 3.6 Flash
1150
Nov 19, 2026
26Kimi K2.7 Code
1146
Nov 19, 2026
27GLM-5.1
1138
Nov 19, 2026
28Claude Opus 4.5 (latest)
1126
Nov 19, 2026
28Kimi K2.6
1126
Nov 19, 2026
30GLM-5V-Turbo
1119
Nov 19, 2026
31GLM-5
1093
Nov 19, 2026
32GPT-5.1 Codex
1086
Jul 23, 2026
33Kimi K2.5
1083
Nov 19, 2026
34GPT-5.5
1060
Nov 19, 2026
35Gemini 3.1 Pro Preview
1038
Nov 19, 2026
36Gemini 3 Flash Preview
1033
Nov 19, 2026
37Grok 4.20 (Non-Reasoning)
1024
Nov 19, 2026
38Claude Sonnet 4.5 (latest)
1020
Nov 19, 2026
38GLM-4.7
1020
Nov 19, 2026
40GPT-5.2
1012
Nov 19, 2026
41GLM-4.6
999
Nov 19, 2026
42GPT-5.4
987
Nov 19, 2026
43Grok 4.3
978
Nov 19, 2026
44GPT-5.2 Codex
963
Nov 19, 2026
45GPT-5.3 Codex
953
Nov 19, 2026
46DeepSeek V4 Pro
948
Jul 23, 2026

Dot = elo on a 920–1531 scale (position, not length). Scores link to model pages; every number keeps its source on the model page.