Design scores
Human-preference votes on generated UI. Measures taste, not whether the code works.
65 results on 1 board · checked
How this category is sourced
Human-preference votes on generated UI. Measures taste, not whether the code works.
- Every value is copied as the board publishes it, with its metric, harness, as-of date and a source link. Boards use different metrics, so numbers are never compared across boards.
- No Ratelimit Now score: we do not normalise, weight or combine results.
- Stale means the as-of date is more than 90 days old. Frozen means the board stopped scoring new models. Preliminary is the board's own label.
- A model's score depends on the harness or agent it ran in. It is not a score for any tool on this site.
- Open and Chinese models sit in the same tables, with the license the board lists. Hosting region is not confirmed for any model.
Latest generation on this page
GPT-6.1 SolDesign ArenaGPT-6 LunaDesign ArenaGPT-6 Astra2 resultsQwen 3.8 Max PreviewDesign ArenaMuse WonderDesign ArenaMuse Spark 1.32 resultsMiniMax M3Design ArenaKimi K3Design ArenaGrok 4.7Design ArenaGemini 4 ArgonDesign ArenaGemini 3.8 FlashDesign ArenaDeepSeek V4.1 Flash 1017Design ArenaDeepSeek V4.1 FlashDesign ArenaClaude Sonnet 5.5Design ArenaClaude Opus 5.5Design ArenaClaude Haiku 5.5Design ArenaClaude Fable 5.1Design Arena
Not on these boards yet: GPT-6 Sol (see their model pages for other categories).
Design Arena (All categories)
Elo (human preference)Harness: Design ArenaNewest as-of 2026-10-2419 latest-gen · 41 current · 24 older · 15 open weights
Human preferencedesignarena.ai
Chart data as a table
| Model | Lab | Elo (human preference) |
|---|---|---|
| claude-opus-5-5 | Anthropic | 1,389 |
| gpt-6-astra | OpenAI | 1,383 |
| muse-wonder-1.0 | Meta | 1,377 |
| gpt-6-astra-max | OpenAI | 1,371 |
| kimi-k3 | Chinese labs | 1,359 |
| gpt-6.1-sol | OpenAI | 1,358 |
| claude-sonnet-5-5 | Anthropic | 1,354 |
| muse-spark-1.3 | Meta | 1,350 |
| muse-spark-1.3-max | Meta | 1,349 |
| claude-fable-5-1 | Anthropic | 1,334 |
Source: designarena.ai
| Lab | Rows |
|---|---|
| OpenAI | 3 |
| Anthropic | 3 |
| Meta | 3 |
| Chinese labs | 1 |
Source: designarena.ai
- New row on the board since the Oct 19 refresh
- Design Arena per-category boards (Website, UI Component, Mobile Apps, Native Apps) require a Bearer API key per Design Arena API docs (https://docs.designarena.ai/api-reference/leaderboard); only the server-rendered All-categories and Fullstack boards were captured.
- Design Arena per-category boards (android, mobile, ui-components) still need an API key
| Board # | Model (as listed) | Elo | Detail | License | As of | Source |
|---|---|---|---|---|---|---|
| 1 | claude-opus-5-5Anthropic · latest gen | 1389 | 6,496 battles | Not listed | ↗ | |
| 2 | gpt-6-astraOpenAI · latest gen | 1383 | 10,786 battles | Not listed | ↗ | |
| 3 | muse-wonder-1.0Meta · latest gen | 1377 | 7,604 battles | Not listed | ↗ | |
| 4 | gpt-6-astra-maxOpenAI · latest gen | 1371 | 3,831 battles | Not listed | ↗ | |
| 5 | kimi-k3Moonshot · latest gen | 1359 | 9,056 battles | Open weightskimi-k3 (custom) | ↗ | |
| 6 | gpt-6.1-solOpenAI · latest gen | 1358 | 5,276 battles | Not listed | ↗ | |
| 7 | claude-sonnet-5-5Anthropic · latest gen | 1354 | 4,735 battles | Not listed | ↗ | |
| 8 | muse-spark-1.3Meta · latest gen | 1350 | 46,492 battles | Not listed | ↗ | |
| 9 | muse-spark-1.3-maxMeta · latest gen | 1349 | 39,572 battles | Not listed | ↗ | |
| 10 | gpt-5.6-sol-xhighOpenAI · older version | 1340 | 13,755 battles | Not listed | ↗ | |
| 11 | claude-fable-5-1Anthropic · latest gen | 1334 | 9,349 battles | Not listed | ↗ | |
| 12 | gemini-4-argonGoogle · latest gen | 1329 | 12,965 battles | Not listed | ↗ | |
| 13 | claude-opus-5Anthropic · older version | 1322 | 19,481 battles | Not listed | ↗ | |
| 14 | deepseek-v4-1-flashDeepSeek · latest gen | 1318 | 42,235 battles | Open weightsmit | ↗ | |
| 15 | hampshire | 1315 | 35,308 battles | Not listed | ↗ | |
| 16 | gpt-5.6-solOpenAI · older version | 1315 | 28,417 battles | Not listed | ↗ | |
| 17 | muse-spark-1.2Meta · older version | 1312 | 50,568 battles | Not listed | ↗ | |
| 18 | claude-fable-5Anthropic · older version | 1309 | 20,217 battles | Not listed | ↗ | |
| 19 | gemini-3.7-flashGoogle · older version | 1308 | 77,618 battles | Not listed | ↗ | |
| 20 | colorado | 1304 | 15,128 battles | Not listed | ↗ | |
| 21 | gemini-3.8-flashGoogle · latest gen | 1302 | 46,277 battles | Not listed | ↗ | |
| 22 | cortado | 1301 | 21,626 battles | Not listed | ↗ | |
| 24 | gpt-6-solOpenAI · older version | 1300 | 5,663 battles | Not listed | ↗ | |
| 24 | deepseek-v4-1-flash-1017DeepSeek · latest gen | 1296 | 4,402 battles | Not listed | ↗ | |
| 26 | qwen3.8-max-previewAlibaba · latest gen | 1292 | 11,396 battles | Not listed | ↗ | |
| 27 | grogu | 1290 | 36,822 battles | Not listed | ↗ | |
| 28 | gemini-3.6-flashGoogle · older version | 1289 | 32,832 battles | Not listed | ↗ | |
| 29 | claude-opus-4-6Anthropic · older version | 1288 | 27,406 battles | Not listed | ↗ | |
| 30 | glm-5.2Z.ai | 1286 | 57,124 battles | Open weightsmit | ↗ | |
| 31 | claude-opus-4-6-thinkingAnthropic · older version | 1284 | 23,814 battles | Not listed | ↗ | |
| 32 | notebook | 1280 | 28,728 battles | Not listed | ↗ | |
| 33 | claude-haiku-5-5Anthropic · latest gen | 1277 | 9,553 battles | Not listed | ↗ | |
| 34 | deca-2.6-ultra | 1276 | 2,450 battles | Not listed | ↗ | |
| 35 | claude-sonnet-5Anthropic · older version | 1275 | 24,519 battles | Not listed | ↗ | |
| 36 | evergreen | 1275 | 23,956 battles | Not listed | ↗ | |
| 36 | claude-sonnet-4-6Anthropic · older version | 1275 | 26,317 battles | Not listed | ↗ | |
| 38 | qwen3.7-maxAlibaba | 1274 | 36,725 battles | Not listed | ↗ | |
| 39 | yoda | 1274 | 37,544 battles | Not listed | ↗ | |
| 40 | grok-4.7SpaceXAI · latest gen | 1271 | 3,025 battles | Not listed | ↗ | |
| 41 | kimi-k2.6Moonshot · older version | 1271 | 34,048 battles | Open weightsmodified-mit | ↗ | |
| 42 | deca-2.5-mini | 1270 | 4,212 battles | Not listed | ↗ | |
| 43 | gpt-6-lunaOpenAI · latest gen | 1269 | 7,483 battles | Not listed | ↗ | |
| 47 | mimo-v2.5-proXiaomi | 1265 | 28,909 battles | Open weightsmit | ↗ | |
| 51 | mimo-v2.5Xiaomi | 1259 | 44,973 battles | Open weightsmit | ↗ | |
| 58 | minimax-m3MiniMax · latest gen | 1245 | 27,874 battles | Open weightsminimax-community | ↗ | |
| 62 | deepseek-v4-proDeepSeek | 1239 | 27,277 battles | Open weightsmit | ↗ | |
| 70 | deepseek-v4-flash-0731DeepSeek | 1228 | 10,439 battles | Open weightsmit | ↗ | |
| 73 | grok-4-20-beta-reasoningSpaceXAI · older version | 1220 | 37,055 battles | Not listed | ↗ | |
| 79 | grok-4-20-beta-non-reasoningSpaceXAI · older version | 1205 | 40,222 battles | Not listed | ↗ | |
| 79 | deepseek-v4-flashDeepSeek | 1204 | 28,104 battles | Open weightsmit | ↗ | |
| 83 | grok-4.3SpaceXAI · older version | 1186 | 41,413 battles | Not listed | ↗ | |
| 118 | nemotron-3-ultra-550b-a55b | 1145 | 26,124 battles | Open weightsopenmdw-1.1 | ↗ | |
| 140 | grok-4-fast-non-reasoningSpaceXAI · older version | 1100 | 36,650 battles | Not listed | ↗ | |
| 143 | grok-4-1-fast-non-reasoningSpaceXAI · older version | 1091 | 33,603 battles | Not listed | ↗ | |
| 144 | grok-4-1-fast-reasoningSpaceXAI · older version | 1086 | 31,135 battles | Not listed | ↗ | |
| 153 | grok-3SpaceXAI · older version | 1052 | 26,869 battles | Not listed | ↗ | |
| 155 | grok-4-fast-reasoningSpaceXAI · older version | 1050 | 37,376 battles | Not listed | ↗ | |
| 163 | grok-4SpaceXAI · older version | 1015 | 24,016 battles | Not listed | ↗ | |
| 168 | grok-code-fast-1SpaceXAI · older version | 998 | 4,299 battles | Not listed | ↗ | |
| 173 | gpt-oss-120bOpenAI | 961 | 5,272 battles | Open weightsapache-2.0 | ↗ | |
| 176 | grok-3-miniSpaceXAI · older version | 930 | 7,621 battles | Not listed | ↗ | |
| 177 | llama-3.1-nemotron-ultra-253b | 928 | 3,173 battles | Not listed | ↗ | |
| 179 | llama-4-maverick | 878 | 1,678 battles | Open weightsllama4 (custom) | ↗ | |
| 183 | devstral-small-2507Mistral | 806 | 1,250 battles | Open weightsapache-2.0 | ↗ | |
| 184 | llama-4-scout | 788 | 1,275 battles | Open weightsllama4 (custom) | ↗ |