Design Arena: PowerPoint slides leaderboard
- models measured
- 30
- lead over #2
- +33 Elo
- median
- 1197
Leader on Design Arena: PowerPoint slides · read October 21
On October 21, 2026, 30 of our catalog's models had a Design Arena: PowerPoint slides result, and Anthropic Claude Fable 5.1 led with 1328.
Design Arena shows people two designs made by two models from the same prompt (a PowerPoint deck made with python-pptx, built by the model as an agent) and asks which is better. The number is the Elo rating built from those votes, as Design Arena publishes it.
Role in the index
We collect this benchmark and show it as supporting evidence. It is not part of the Vibe Coding Index, because it measures something other than coding and the index is about coding. Read the methodology
| # | Model | Result | Battles | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1Anthropic | 1328 | 768 | 89.1 | $50.00 | |
| 2 | Claude Fable 5Anthropic | 1295 | 1,914 | 82.1 | $50.00 | |
| 3 | Kimi K3Moonshot AI | 1273 | 3,282 | 61.8 | $11.936 | |
| 4 | Claude Opus 5Anthropic | 1265 | 606 | 81.8 | $25.00 | |
| 5 | Qwen3.8 Max (0902)Qwen | 1257 | 386 | 63.5 | $6.00 | |
| 6 | GLM 5.3Z.ai | 1255 | 248 | 73.1 | $1.40 | |
| 7 | GPT-6 AstraOpenAI | 1245 | 804 | 88.7 | $50.00 | |
| 8 | Muse Spark 1.3Meta | 1244 | 3,773 | 79.7 | $4.25 | |
| 9 | Grok 4.6xAI | 1241 | Not published | 76.4 | $6.00 | |
| 10 | GPT-5.6 SolOpenAI | 1240 | 1,215 | 76.7 | $20.00 | |
| 11 | Grok 4.5xAI | 1232 | Not published | 75.5 | $6.00 | |
| 12 | Claude Opus 4.8Anthropic | 1227 | 1,494 | 66.0 | $25.00 | |
| 13 | Claude Sonnet 5Anthropic | 1216 | 2,132 | 63.5 | $10.00 | |
| 14 | MiniMax M3MiniMax | 1205 | 1,060 | 57.8 | $1.20 | |
| 15 | Muse Spark 1.2Meta | 1198 | 1,755 | 65.1 | $4.25 | |
| 16 | Qwen3.7 MaxQwen | 1196 | 956 | 45.1 | $4.425 | |
| 17 | GLM 5.2Z.ai | 1195 | 1,172 | 57.7 | $7.00 | |
| 18 | GLM 5.1Z.ai | 1189 | 1,935 | 44.0 | $4.40 | |
| 19 | Gemini 3.5 FlashGoogle | 1178 | 4,049 | 42.8 | $9.00 | |
| 20 | Gemini 3.8 FlashGoogle | 1178 | 821 | 70.5 | $4.125 | |
| 21 | Muse Spark 1.1Meta | 1156 | Not published | 48.9 | $4.25 | |
| 22 | Kimi K2.7 CodeMoonshot AI | 1154 | 836 | 39.1 | $3.35 | |
| 23 | GLM 5V TurboZ.ai | 1152 | 775 | 28.8 | $4.00 | |
| 24 | Gemini 3.6 FlashGoogle | 1146 | 858 | 48.3 | $3.75 | |
| 25 | GPT-5.6 TerraOpenAI | 1130 | 871 | 69.0 | $12.00 | |
| 26 | Kimi K2.6Moonshot AI | 1128 | 1,728 | 44.2 | $3.41 | |
| 27 | GPT-5.5OpenAI | 1108 | 1,237 | 67.8 | $30.00 | |
| 28 | Gemini 3.1 Pro PreviewGoogle | 1064 | 1,349 | 35.3 | $12.00 | |
| 29 | Gemini 3 Flash PreviewGoogle | 1036 | Not published | 75.8 | $3.00 | |
| 30 | Grok 4.3xAI | 1012 | 898 | 22.5 | $2.50 |
Only models in our catalog are listed, and each appears once with its best published run. 141 rows were read from the source on October 21, 2026, and rows that match no catalog model are left out. Every other column is a figure the board publishes for the same run.