llm.ing

Design Arena — mobileapps

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 5
1348
Sep 4, 2026
2Claude Fable 5
1293
Sep 20, 2026
3Kimi K3
1280
Sep 20, 2026
4Grok 4.6
1268
Sep 20, 2026
5Qwen3.8 Max
1261
Sep 3, 2026
6Gemini 3.7 Flash
1260
Sep 21, 2026
7Gemini 3.8 Flash
1256
Sep 21, 2026
8Claude Opus 4.8
1253
Sep 21, 2026
9Claude Sonnet 5
1249
Sep 21, 2026
10Grok 4.5
1245
Sep 21, 2026
11Claude Sonnet 4.6
1241
Sep 19, 2026
12Claude Opus 4.6
1238
Sep 19, 2026
13Muse Spark 1.3
1231
Sep 21, 2026
14Gemini 3.6 Flash
1227
Sep 20, 2026
15GLM-5.3
1223
Sep 19, 2026
16Claude Opus 4.5 (latest)
1218
Sep 19, 2026
17Muse Spark 1.1
1206
Sep 20, 2026
18Gemini 3.5 Flash
1201
Sep 20, 2026
19MiniMax-M3
1195
Sep 19, 2026
19Muse Spark 1.2
1195
Sep 21, 2026
21GLM-5.1
1194
Sep 21, 2026
22GPT-5.1 Codex
1191
Aug 4, 2026
22GLM-5.2
1191
Sep 20, 2026
24Kimi K2.6
1181
Sep 21, 2026
25Qwen3.7 Max
1176
Sep 19, 2026
25Kimi K2.5
1176
Sep 19, 2026
27Kimi K2.7 Code
1174
Sep 21, 2026
28GPT-5.5
1171
Sep 21, 2026
29Claude Sonnet 4.5 (latest)
1167
Sep 20, 2026
30GLM-5
1165
Sep 19, 2026
31GLM-5V-Turbo
1163
Sep 19, 2026
32GLM-4.7
1135
Sep 21, 2026
33GPT-5-Codex
1126
Jul 29, 2026
33GLM-4.6
1126
Sep 21, 2026
35GPT-5.2
1123
Sep 19, 2026
36Gemini 3.1 Pro Preview
1121
Sep 19, 2026
37Gemini 3 Flash Preview
1120
Sep 21, 2026
38GPT-5.2 Codex
1119
Sep 19, 2026
38Grok 4.20 (Non-Reasoning)
1119
Sep 19, 2026
40GPT-5.1
1117
Aug 3, 2026
41GPT-5.4
1116
Sep 19, 2026
42Grok 4.3
1091
Sep 20, 2026
43GPT-5.3 Codex
1083
Sep 19, 2026

Dot = elo on a 1069–1362 scale (position, not length). Scores link to model pages; every number keeps its source on the model page.