llm.ing

Design Arena — godotgamedev

mirrorrun by Design Arenaunit: elo31 modelssource ↗

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

websitecodecategoriesdatavizuicomponentgamedev3dsvgasciiartfullstackmobileapps+15 more
#ModelScoreObserved
1Claude Fable 5
1307
Sep 19, 2026
2Claude Opus 5
1275
Sep 19, 2026
3Claude Opus 4.7
1270
Jul 23, 2026
4Claude Sonnet 5
1238
Sep 19, 2026
5Claude Opus 4.8
1236
Sep 19, 2026
5Gemini 3.1 Pro Preview
1236
Jul 23, 2026
5Grok 4.5
1236
Sep 19, 2026
8Claude Sonnet 4.6
1226
Jul 23, 2026
9Kimi K2.5
1219
Jul 23, 2026
10Muse Spark 1.3
1214
Sep 19, 2026
11Kimi K3
1199
Jul 23, 2026
12Qwen3.7 Max
1196
Sep 19, 2026
13GPT-5.5
1183
Sep 19, 2026
14GLM-4.6
1180
Jul 23, 2026
15Gemini 3 Flash Preview
1161
Jul 23, 2026
16Kimi K2.7 Code
1156
Sep 19, 2026
17GLM-5
1144
Jul 23, 2026
18GPT-5.2 Codex
1142
Jul 23, 2026
18GPT-5.2
1142
Jul 23, 2026
18GLM-5.2
1142
Jul 23, 2026
21GPT-5.4
1135
Jul 23, 2026
22Kimi K2.6
1131
Sep 19, 2026
23GPT-5.3 Codex
1124
Jul 23, 2026
24Muse Spark 1.1
1113
Sep 19, 2026
25Gemini 3.5 Flash
1108
Sep 19, 2026
26GLM-5.1
1104
Jul 23, 2026
27Grok 4.20 (Non-Reasoning)
1089
Jul 23, 2026
28DeepSeek V4 Pro
1059
Jul 23, 2026
29GLM-4.7
1058
Jul 23, 2026
30Grok 4.3
1035
Jul 23, 2026
31GLM-5V-Turbo
970
Sep 19, 2026

Dot = elo on a 953–1324 scale (position, not length). Scores link to model pages; every number keeps its source on the model page.