Design Arena — agenticgamedev
Caveat: Head-to-head human votes on generated designs/code, mirrored via OpenRouter.
| # | Model | Score | Observed | |
|---|---|---|---|---|
| 1 | Claude Fable 5Anthropic | 1307 | Jul 23, 2026 | |
| 2 | Claude Opus 4.8Anthropic | 1262 | Jul 24, 2026 | |
| 3 | Claude Opus 4.7Anthropic | 1260 | Jul 23, 2026 | |
| 4 | Claude Sonnet 5Anthropic | 1241 | Jul 24, 2026 | |
| 5 | Grok 4.5xAI | 1223 | Jul 24, 2026 | |
| 6 | MiniMax-M3MiniMax (minimax.io) | 1216 | Jul 24, 2026 | |
| 7 | Claude Sonnet 4.6Anthropic | 1210 | Jul 23, 2026 | |
| 8 | Muse Spark 1.1Meta | 1196 | Jul 23, 2026 | |
| 9 | GLM-5.2Zhipu AI | 1193 | Jul 24, 2026 | |
| 10 | GPT-5.5OpenAI | 1192 | Jul 23, 2026 | |
| 11 | Gemini 3.5 FlashGoogle | 1191 | Jul 23, 2026 | |
| 12 | GLM-5.1Zhipu AI | 1182 | Jul 23, 2026 | |
| 13 | Qwen3.7 MaxAlibaba | 1181 | Jul 24, 2026 | |
| 14 | Kimi K2.6Moonshot AI | 1157 | Jul 24, 2026 | |
| 15 | Kimi K2.7 CodeMoonshot AI | 1147 | Jul 24, 2026 | |
| 16 | Gemini 3.1 Pro PreviewGoogle | 1128 | Jul 23, 2026 | |
| 17 | GLM-5V-TurboZhipu AI | 1105 | Jul 23, 2026 | |
| 18 | Grok 4.3xAI | 1016 | Jul 24, 2026 |
Dot = elo on a 1001–1322 scale (position, not length). Scores link to model pages; every number keeps its source on the model page.