llm.ing

Design Arena — fullstack

mirrorrun by Design Arenaunit: elo43 modelssource ↗

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

websitecodecategoriesdatavizuicomponentgamedev3dsvgasciiartfullstackmobileapps+15 more
#ModelScoreObserved
1Claude Opus 4.7
1503
Jul 23, 2026
2Claude Fable 5.1
1336
Sep 19, 2026
3Qwen3.8 Max
1332
Sep 4, 2026
4Kimi K3
1330
Sep 21, 2026
5Muse Spark 1.3
1318
Sep 19, 2026
6Claude Opus 5
1314
Sep 21, 2026
7Claude Fable 5
1287
Sep 20, 2026
8Grok 4.6
1274
Sep 20, 2026
9Claude Sonnet 5
1260
Sep 18, 2026
10Grok 4.5
1259
Sep 20, 2026
11Claude Opus 4.8
1256
Sep 19, 2026
12GLM-5.2
1252
Sep 21, 2026
13Gemini 3.8 Flash
1250
Sep 19, 2026
14Claude Opus 4.6
1229
Sep 19, 2026
15Claude Sonnet 4.6
1223
Sep 16, 2026
16Gemini 3.7 Flash
1221
Sep 20, 2026
17Muse Spark 1.2
1219
Sep 19, 2026
18Gemini 3.5 Flash
1208
Sep 15, 2026
19Muse Spark 1.1
1207
Sep 21, 2026
20MiniMax-M3
1204
Sep 20, 2026
21Qwen3.7 Max
1202
Sep 21, 2026
22Gemini 3.6 Flash
1190
Sep 21, 2026
23Kimi K2.7 Code
1186
Sep 21, 2026
24GLM-5.1
1177
Sep 21, 2026
25Claude Opus 4.5 (latest)
1166
Sep 15, 2026
26Kimi K2.6
1165
Sep 21, 2026
27GLM-5V-Turbo
1159
Sep 16, 2026
28GLM-5
1133
Sep 20, 2026
29Kimi K2.5
1124
Sep 20, 2026
30GPT-5.5
1099
Sep 19, 2026
31GPT-5.1 Codex
1086
Jul 23, 2026
32Gemini 3.1 Pro Preview
1079
Sep 20, 2026
33Gemini 3 Flash Preview
1073
Sep 16, 2026
34Grok 4.20 (Non-Reasoning)
1063
Sep 15, 2026
35Claude Sonnet 4.5 (latest)
1060
Sep 16, 2026
36GLM-4.7
1059
Sep 15, 2026
37GPT-5.2
1052
Sep 15, 2026
38GLM-4.6
1039
Sep 16, 2026
39GPT-5.4
1027
Sep 17, 2026
40Grok 4.3
1017
Sep 16, 2026
41GPT-5.2 Codex
1002
Sep 15, 2026
42GPT-5.3 Codex
993
Sep 17, 2026
43DeepSeek 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.