# Design Arena Website leaderboard

Multimodal & Grounded benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/multimodal-grounded-design-arena-website

Design Arena Website Elo. Every model the catalog carries a published Design Arena Website value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Multimodal & Grounded |
| Measure | Elo |
| Tasks | Website generation comparisons |
| Difficulty | Design and website generation |
| Published by | [OpenRouter Grok 4.3 benchmarks](https://openrouter.ai/x-ai/grok-4.3/benchmarks) |

A display-only Design Arena website-generation Elo score surfaced on OpenRouter model benchmark pages.

## Design Arena Website ranking

113 models with a published Design Arena Website value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Elo | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [Muse Wonder](https://modelscale.dev/models/muse-wonder) | Meta | 1376 | Observed 2026-11-21 · source benchlm:models |
| 2 | [Muse Spark 1.3](https://modelscale.dev/models/muse-spark-1-3) | Meta | 1357 | Observed 2026-11-21 · source benchlm:models |
| 3 | [Claude Fable 5.2](https://modelscale.dev/models/claude-fable-5-2) | Anthropic | 1348 | Observed 2026-11-21 · source benchlm:models |
| 4 | [Kimi K3](https://modelscale.dev/models/kimi-3) | Moonshot AI | 1335 | Observed 2026-11-21 · source benchlm:models |
| 5 | [Gemini 4 Hydrogen](https://modelscale.dev/models/gemini-4-hydrogen) | Google | 1331 | Observed 2026-11-21 · source benchlm:models |
| 6 | [Muse Ember](https://modelscale.dev/models/muse-ember) | Meta | 1327 | Observed 2026-11-21 · source benchlm:models |
| 7 | [Claude Opus 5.5](https://modelscale.dev/models/claude-opus-5-5) | Anthropic | 1322 | Observed 2026-11-21 · source benchlm:models |
| 8 | [Kimi K3.1 Pro](https://modelscale.dev/models/kimi-3-1-pro) | Moonshot AI | 1316 | Observed 2026-11-21 · source benchlm:models |
| 9 | [Gemini 4 Argon](https://modelscale.dev/models/gemini-4-argon) | Google | 1313 | Observed 2026-11-21 · source benchlm:models |
| 9 | [GPT-6.1 Sol](https://modelscale.dev/models/gpt-6-1-sol) | OpenAI | 1313 | Observed 2026-11-21 · source benchlm:models |
| 11 | [MiMo-V2.6-Pro](https://modelscale.dev/models/mimo-v2-6-pro) | Xiaomi | 1308 | Observed 2026-11-21 · source benchlm:models |
| 12 | [Gemini 4 Carbon](https://modelscale.dev/models/gemini-4-carbon) | Google | 1307 | Observed 2026-11-21 · source benchlm:models |
| 13 | [Muse Spark 1.2](https://modelscale.dev/models/muse-spark-1-2) | Meta | 1306 | Observed 2026-11-21 · source benchlm:models |
| 14 | [Claude Sonnet 5.5](https://modelscale.dev/models/claude-sonnet-5-5) | Anthropic | 1305 | Observed 2026-11-21 · source benchlm:models |
| 15 | [Muse Spark Open](https://modelscale.dev/models/muse-spark-open) | Meta | 1303 | Observed 2026-11-21 · source benchlm:models |
| 16 | [Claude Fable 5.1](https://modelscale.dev/models/claude-fable-5-1) | Anthropic | 1302 | Observed 2026-11-21 · source benchlm:models |
| 17 | [Claude Opus 5](https://modelscale.dev/models/claude-opus-5) | Anthropic | 1301 | Observed 2026-11-21 · source benchlm:models |
| 18 | [Gemini 3.7 Flash](https://modelscale.dev/models/gemini-3-7-flash) | Google | 1292 | Observed 2026-11-21 · source benchlm:models |
| 19 | [DeepSeek V4.1 Flash 1017](https://modelscale.dev/models/deepseek-v4-1-flash) | DeepSeek | 1290 | Observed 2026-11-21 · source benchlm:models |
| 19 | [GLM-5.1](https://modelscale.dev/models/glm-5-1) | Z.AI | 1290 | Observed 2026-11-21 · source benchlm:models |
| 21 | [Gemini 3.6 Flash](https://modelscale.dev/models/gemini-3-6-flash) | Google | 1289 | Observed 2026-11-21 · source benchlm:models |
| 22 | [Gemini 3.8 Flash](https://modelscale.dev/models/gemini-3-8-flash) | Google | 1288 | Observed 2026-11-21 · source benchlm:models |
| 23 | [Claude Fable 5](https://modelscale.dev/models/claude-fable-5) | Anthropic | 1285 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Claude Opus 4.6](https://modelscale.dev/models/claude-opus-4-6) | Anthropic | 1280 | Observed 2026-11-21 · source benchlm:models |
| 24 | [Claude Opus 4.6 (Adaptive)](https://modelscale.dev/models/claude-opus-4-6-thinking) | Anthropic | 1280 | Observed 2026-11-21 · source benchlm:models |
| 26 | [GLM-5.3](https://modelscale.dev/models/glm-5-3) | Z.AI | 1275 | Observed 2026-11-21 · source benchlm:models |
| 27 | [Claude Sonnet 4.6](https://modelscale.dev/models/claude-sonnet-4-6) | Anthropic | 1274 | Observed 2026-11-21 · source benchlm:models |
| 28 | [GLM-5.2](https://modelscale.dev/models/glm-5-2) | Z.AI | 1273 | Observed 2026-11-21 · source benchlm:models |
| 28 | [Grok 4.6](https://modelscale.dev/models/grok-4-6) | xAI | 1273 | Observed 2026-11-21 · source benchlm:models |
| 30 | [Grok 4.5](https://modelscale.dev/models/grok-4-5) | xAI | 1270 | Observed 2026-11-21 · source benchlm:models |
| 31 | [Claude Sonnet 5](https://modelscale.dev/models/claude-sonnet-5) | Anthropic | 1265 | Observed 2026-11-21 · source benchlm:models |
| 32 | [Qwen3.7 Max](https://modelscale.dev/models/qwen3-7-max) | Alibaba | 1264 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Kimi K2.6](https://modelscale.dev/models/kimi-2-6) | Moonshot AI | 1260 | Observed 2026-11-21 · source benchlm:models |
| 33 | [Muse Spark 1.1](https://modelscale.dev/models/muse-spark-1-1) | Meta | 1260 | Observed 2026-11-21 · source benchlm:models |
| 35 | [MiMo-V2.5-Pro](https://modelscale.dev/models/mimo-v2-5-pro) | Xiaomi | 1259 | Observed 2026-11-21 · source benchlm:models |
| 36 | [DeepSeek V4 Pro 0813](https://modelscale.dev/models/deepseek-v4-pro-max) | DeepSeek | 1258 | Last good 2026-11-18 · source benchlm:models |
| 36 | [Qwen3.7 Plus](https://modelscale.dev/models/qwen3-7-plus) | Alibaba | 1258 | Observed 2026-11-21 · source benchlm:models |
| 38 | [Gemini 3.5 Flash](https://modelscale.dev/models/gemini-3-5-flash) | Google | 1257 | Observed 2026-11-21 · source benchlm:models |
| 38 | [MiMo-V2.5](https://modelscale.dev/models/mimo-v2-5) | Xiaomi | 1257 | Observed 2026-11-21 · source benchlm:models |
| 40 | [Mistral Large 4](https://modelscale.dev/models/mistral-large-4) | Mistral | 1255 | Observed 2026-11-21 · source benchlm:models |
| 41 | [Kimi K2.7 Code](https://modelscale.dev/models/kimi-k2-7-code) | Moonshot AI | 1254 | Observed 2026-11-21 · source benchlm:models |
| 42 | [GLM-5.3-Flash](https://modelscale.dev/models/glm-5-3-flash) | Z.AI | 1253 | Observed 2026-11-21 · source benchlm:models |
| 43 | [GLM-5-Turbo](https://modelscale.dev/models/glm-5-turbo) | Z.AI | 1251 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Claude Haiku 5.5](https://modelscale.dev/models/claude-haiku-5-5) | Anthropic | 1249 | Observed 2026-11-21 · source benchlm:models |
| 44 | [Hy4](https://modelscale.dev/models/hy4) | Tencent | 1249 | Observed 2026-11-21 · source benchlm:models |
| 46 | [Claude Opus 4.8](https://modelscale.dev/models/claude-opus-4-8) | Anthropic | 1247 | Observed 2026-11-21 · source benchlm:models |
| 47 | [MiniMax M3](https://modelscale.dev/models/minimax-m3) | MiniMax | 1246 | Observed 2026-11-21 · source benchlm:models |
| 48 | [GPT-5.5](https://modelscale.dev/models/gpt-5-5) | OpenAI | 1245 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Gemini 3.1 Pro](https://modelscale.dev/models/gemini-3-1-pro) | Google | 1241 | Observed 2026-11-21 · source benchlm:models |
| 49 | [Grok 4.7](https://modelscale.dev/models/grok-4-7) | xAI | 1241 | Observed 2026-11-21 · source benchlm:models |
| 51 | [Kimi K2.5 (Reasoning)](https://modelscale.dev/models/kimi-k2-5-reasoning) | Moonshot AI | 1240 | Last good 2026-11-18 · source benchlm:models |
| 52 | [GLM-5 (Reasoning)](https://modelscale.dev/models/glm-5-reasoning) | Z.AI | 1238 | Last good 2026-11-18 · source benchlm:models |
| 53 | [Kimi K2.5](https://modelscale.dev/models/kimi-k2-5) | Moonshot AI | 1237 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Claude Opus 4.5](https://modelscale.dev/models/claude-opus-4-5) | Anthropic | 1236 | Observed 2026-11-21 · source benchlm:models |
| 54 | [Claude Opus 4.5 Thinking](https://modelscale.dev/models/claude-opus-4-5-thinking) | Anthropic | 1236 | Observed 2026-11-21 · source benchlm:models |
| 54 | [GLM-5](https://modelscale.dev/models/glm-5) | Z.AI | 1236 | Observed 2026-11-21 · source benchlm:models |
| 57 | [Beam 1.0 501B-A23B](https://modelscale.dev/models/reflection-beam) | Reflection AI | 1235 | Observed 2026-11-21 · source benchlm:models |
| 58 | [MiniMax M2.7](https://modelscale.dev/models/minimax-m2-7) | MiniMax | 1231 | Observed 2026-11-21 · source benchlm:models |
| 58 | [Qwen3.6 Plus](https://modelscale.dev/models/qwen3-6-plus) | Alibaba | 1231 | Observed 2026-11-21 · source benchlm:models |
| 60 | [Hy4 flash](https://modelscale.dev/models/hy4-flash) | Tencent | 1228 | Observed 2026-11-21 · source benchlm:models |
| 61 | [GLM-5V-Turbo](https://modelscale.dev/models/glm-5v-turbo) | Z.AI | 1219 | Observed 2026-11-21 · source benchlm:models |
| 62 | [Grok 4.20](https://modelscale.dev/models/grok-4-20-beta) | xAI | 1218 | Observed 2026-11-21 · source benchlm:models |
| 63 | [GLM-4.7](https://modelscale.dev/models/glm-4-7) | Z.AI | 1214 | Observed 2026-11-21 · source benchlm:models |
| 64 | [Inkling](https://modelscale.dev/models/inkling) | Thinking Machines Lab | 1212 | Observed 2026-11-21 · source benchlm:models |
| 65 | [GPT-5.4](https://modelscale.dev/models/gpt-5-4) | OpenAI | 1209 | Observed 2026-11-21 · source benchlm:models |
| 66 | [DeepSeek V4 Flash 0731](https://modelscale.dev/models/deepseek-v4-flash-max) | DeepSeek | 1196 | Observed 2026-11-21 · source benchlm:models |
| 67 | [Gemini 3 Flash](https://modelscale.dev/models/gemini-3-flash) | Google | 1185 | Observed 2026-11-21 · source benchlm:models |
| 68 | [GPT-5.2](https://modelscale.dev/models/gpt-5-2) | OpenAI | 1183 | Observed 2026-11-21 · source benchlm:models |
| 68 | [Grok 4.3](https://modelscale.dev/models/grok-4-3) | xAI | 1183 | Observed 2026-11-21 · source benchlm:models |
| 68 | [Step 3.7 Flash](https://modelscale.dev/models/step-3-7-flash) | StepFun | 1183 | Observed 2026-11-21 · source benchlm:models |
| 71 | [Muse Glimmer 30B](https://modelscale.dev/models/muse-glimmer-30b) | Meta | 1179 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Claude Sonnet 4.5](https://modelscale.dev/models/claude-sonnet-4-5) | Anthropic | 1178 | Observed 2026-11-21 · source benchlm:models |
| 72 | [Claude Sonnet 4.5 Thinking](https://modelscale.dev/models/claude-sonnet-4-5-thinking) | Anthropic | 1178 | Observed 2026-11-21 · source benchlm:models |
| 74 | [GPT-5.1](https://modelscale.dev/models/gpt-5-1) | OpenAI | 1176 | Observed 2026-11-21 · source benchlm:models |
| 75 | [GPT-5 (high)](https://modelscale.dev/models/gpt-5-high) | OpenAI | 1175 | Last good 2026-11-18 · source benchlm:models |
| 75 | [GPT-5 (medium)](https://modelscale.dev/models/gpt-5-medium) | OpenAI | 1175 | Last good 2026-11-18 · source benchlm:models |
| 77 | [GPT-5](https://modelscale.dev/models/gpt-5) | OpenAI | 1173 | Observed 2026-11-21 · source benchlm:models |
| 78 | [Hy3](https://modelscale.dev/models/hy3) | Tencent | 1170 | Observed 2026-11-21 · source benchlm:models |
| 79 | [Claude 4.1 Opus](https://modelscale.dev/models/claude-4-1-opus) | Anthropic | 1166 | Observed 2026-11-21 · source benchlm:models |
| 79 | [DeepSeek V3.2 (Thinking)](https://modelscale.dev/models/deepseek-v3-2-thinking) | DeepSeek | 1166 | Last good 2026-11-18 · source benchlm:models |
| 81 | [DeepSeek V3.2](https://modelscale.dev/models/deepseek-v3-2) | DeepSeek | 1164 | Observed 2026-11-21 · source benchlm:models |
| 82 | [Solar Pro 4](https://modelscale.dev/models/solar-pro-4) | Upstage | 1160 | Observed 2026-11-21 · source benchlm:models |
| 83 | [GLM-4.5](https://modelscale.dev/models/glm-4-5) | Z.AI | 1158 | Observed 2026-11-21 · source benchlm:models |
| 84 | [Gemini 2.5 Pro](https://modelscale.dev/models/gemini-2-5-pro) | Google | 1156 | Observed 2026-11-21 · source benchlm:models |
| 85 | [Claude 4 Sonnet](https://modelscale.dev/models/claude-4-sonnet) | Anthropic | 1152 | Last good 2026-10-08 · source benchlm:models |
| 86 | [GPT-5.1-Codex](https://modelscale.dev/models/gpt-5-1-codex) | OpenAI | 1151 | Observed 2026-11-21 · source benchlm:models |
| 86 | [GPT-5.3 Codex](https://modelscale.dev/models/gpt-5-3-codex) | OpenAI | 1151 | Observed 2026-11-21 · source benchlm:models |
| 88 | [Qwen3-Coder 480B-A35B](https://modelscale.dev/models/qwen3-coder-480b-a35b) | Alibaba | 1147 | Observed 2026-11-21 · source benchlm:models |
| 89 | [DeepSeek-R1-0528](https://modelscale.dev/models/deepseek-r1-0528) | DeepSeek | 1138 | Observed 2026-11-21 · source benchlm:models |
| 90 | [Trinity-Large-Preview](https://modelscale.dev/models/trinity-large-preview) | Arcee AI | 1137 | Last good 2026-10-23 · source benchlm:models |
| 90 | [Trinity-Large-Thinking](https://modelscale.dev/models/trinity-large-thinking) | Arcee AI | 1137 | Last good 2026-10-23 · source benchlm:models |
| 92 | [GLM-4.5-Air](https://modelscale.dev/models/glm-4-5-air) | Z.AI | 1135 | Observed 2026-11-21 · source benchlm:models |
| 93 | [Nemotron 3 Ultra](https://modelscale.dev/models/nemotron-3-ultra-500b) | NVIDIA | 1126 | Observed 2026-11-21 · source benchlm:models |
| 94 | [Qwen3 Max](https://modelscale.dev/models/qwen3-max) | Alibaba | 1125 | Last good 2026-10-08 · source benchlm:models |
| 95 | [DeepSeek V3.1 (Reasoning)](https://modelscale.dev/models/deepseek-v3-1-reasoning) | DeepSeek | 1113 | Last good 2026-11-18 · source benchlm:models |
| 96 | [Claude Haiku 4.5](https://modelscale.dev/models/claude-haiku-4-5) | Anthropic | 1111 | Observed 2026-11-21 · source benchlm:models |
| 96 | [Claude Haiku 4.5 Thinking](https://modelscale.dev/models/claude-haiku-4-5-thinking) | Anthropic | 1111 | Observed 2026-11-21 · source benchlm:models |
| 96 | [DeepSeek V3.1](https://modelscale.dev/models/deepseek-v3-1) | DeepSeek | 1111 | Observed 2026-11-21 · source benchlm:models |
| 99 | [DeepSeek V3](https://modelscale.dev/models/deepseek-v3) | DeepSeek | 1109 | Observed 2026-11-21 · source benchlm:models |
| 100 | [Gemini 2.5 Flash](https://modelscale.dev/models/gemini-2-5-flash) | Google | 1104 | Observed 2026-11-21 · source benchlm:models |
| 101 | [Mistral Medium 3](https://modelscale.dev/models/mistral-medium-3) | Mistral | 1068 | Observed 2026-11-21 · source benchlm:models |
| 102 | [Kimi K2](https://modelscale.dev/models/kimi-k2) | Moonshot AI | 1039 | Observed 2026-11-21 · source benchlm:models |
| 103 | [GPT-4.1](https://modelscale.dev/models/gpt-4-1) | OpenAI | 1027 | Observed 2026-11-21 · source benchlm:models |
| 104 | [o3](https://modelscale.dev/models/o3) | OpenAI | 1025 | Observed 2026-11-21 · source benchlm:models |
| 105 | [GPT-4.1 mini](https://modelscale.dev/models/gpt-4-1-mini) | OpenAI | 986 | Observed 2026-11-21 · source benchlm:models |
| 106 | [o4-mini (high)](https://modelscale.dev/models/o4-mini-high) | OpenAI | 976 | Last good 2026-11-18 · source benchlm:models |
| 107 | [o4-mini](https://modelscale.dev/models/o4-mini) | OpenAI | 974 | Observed 2026-11-21 · source benchlm:models |
| 108 | [GPT-4.1 nano](https://modelscale.dev/models/gpt-4-1-nano) | OpenAI | 962 | Observed 2026-11-21 · source benchlm:models |
| 109 | [GPT-OSS 120B](https://modelscale.dev/models/gpt-oss-120b) | OpenAI | 957 | Observed 2026-11-21 · source benchlm:models |
| 110 | [Llama 4 Maverick](https://modelscale.dev/models/llama-4-maverick) | Meta | 860 | Observed 2026-11-21 · source benchlm:models |
| 111 | [GPT-OSS 20B](https://modelscale.dev/models/gpt-oss-20b) | OpenAI | 841 | Observed 2026-11-21 · source benchlm:models |
| 112 | [GPT-4o](https://modelscale.dev/models/gpt-4o) | OpenAI | 820 | Observed 2026-11-21 · source benchlm:models |
| 113 | [Llama 4 Scout](https://modelscale.dev/models/llama-4-scout) | Meta | 739 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
