llm.ing

Design Arena — python-pptxslides

mirrorrun by Design Arenaunit: elo29 modelssource ↗

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

websitecodecategoriesgamedev3duicomponentdatavizsvgasciiartmobileappswebapps+19 more
#ModelScoreObserved
1Claude Opus 4.7
1336
Jul 23, 2026
2Claude Fable 5.1
1318
Nov 18, 2026
3Claude Opus 4.8
1298
Jul 23, 2026
4Kimi K3.1 Pro
1287
Nov 19, 2026
5Claude Fable 5
1269
Nov 19, 2026
6GLM-5.1
1258
Jul 23, 2026
7Gemini 3.5 Flash
1247
Jul 23, 2026
8Claude Opus 5
1224
Nov 17, 2026
9Kimi K3
1223
Nov 19, 2026
10GLM-5.3
1217
Nov 16, 2026
11Grok 4.6
1214
Nov 19, 2026
12Muse Spark 1.3
1211
Nov 18, 2026
13Grok 4.5
1198
Nov 19, 2026
14Kimi K2.6
1180
Jul 23, 2026
15Claude Sonnet 5
1179
Nov 19, 2026
16MiniMax-M3
1167
Nov 18, 2026
17GLM-5V-Turbo
1165
Sep 5, 2026
18GLM-5.2
1161
Nov 19, 2026
19Muse Spark 1.2
1157
Nov 18, 2026
20Qwen3.7 Max
1154
Nov 19, 2026
21GPT-5.5
1152
Jul 23, 2026
22Gemini 3.8 Flash
1149
Nov 19, 2026
23Muse Spark 1.1
1124
Nov 19, 2026
24Kimi K2.7 Code
1120
Nov 19, 2026
25Gemini 3.1 Pro Preview
1109
Jul 23, 2026
26Gemini 3.6 Flash
1106
Nov 19, 2026
27Grok 4.3
1072
Jul 23, 2026
28Gemini 3.7 Flash
1055
Nov 19, 2026
29Gemini 3 Flash Preview
1036
Aug 18, 2026

Dot = elo on a 1021–1351 scale (position, not length). Scores link to model pages; every number keeps its source on the model page.