Design & GenerationStill discriminating

Design Arena: Code

Blind human preference for models generating code across common front-end tasks.

  • 127 models have a score, from Design Arena.
  • The leader is Meta: Muse Wonder at 1383 Elo.
  • The top 10 are within 59 Elo of each other.
  • A score on this page last changed on Nov 12, 2026.

Metric

elo (Elo)

Status

Still discriminating

Category

Design & Generation

Maintainer

Design Arena (designarena.ai)

What it tests

Which model produces the best code across common front-end tasks, judged by blind human pairwise voting. Design Arena shows a voter two anonymous models' outputs for the same prompt and asks which is better, so it measures real output quality on a generation task rather than a multiple-choice proxy. This is directly the kind of work a generative product is asked to do.

How it works

A voter submits a prompt, two anonymous models each produce an output, and the voter picks the winner. Votes are aggregated into an Elo rating per model in this category, alongside a win rate and a rank, using the same Bradley-Terry method as chat arenas applied to design and code generation.

How to read a score

Higher Elo is better, and ratings are relative, so a gap of tens of points is within noise and only large gaps separate models. Read it next to the win rate. It reflects human taste and the category's prompt distribution, not objective correctness.

Limitations

Human preference is subjective and can reward flashy output; each category's prompt set is curated and evolves; vote volume differs by category, so lower-traffic categories are noisier.

Leaderboard

Checked Nov 12, 2026, 07:00 UTC · scores last changed Nov 12, 2026

Best Design Arena: Code score per model, ranked. Each score links to its source.

#ModelArena ScoreSource
1Meta: Muse Wonder1383 Elodesignarena
2Anthropic: Claude Opus 5.51381 Elodesignarena
3Anthropic: Claude Fable 5.21368 Elodesignarena
4OpenAI: GPT-6.1 Sol1354 Elodesignarena
5MoonshotAI: Kimi K3.1 Pro1350 Elodesignarena
6MoonshotAI: Kimi K31347 Elodesignarena
7Anthropic: Claude Sonnet 5.51346 Elodesignarena
8Meta: Muse Spark 1.31345 Elodesignarena
9Anthropic: Claude Fable 5.11329 Elodesignarena
10Google: Gemini 4 Argon1324 Elodesignarena
11Anthropic: Claude Opus 51318 Elodesignarena
12Xiaomi: MiMo-V2.6-Pro1310 Elodesignarena
13Meta: Muse Spark 1.21306 Elodesignarena
14Anthropic: Claude Fable 51304 Elodesignarena
15Google: Gemini 3.7 Flash1301 Elodesignarena
16Google: Gemini 3.8 Flash1296 Elodesignarena
17Meta: Muse Spark Open1296 Elodesignarena
18DeepSeek: DeepSeek V4.1 Flash 10171289 Elodesignarena
19Z.ai: GLM 5.31288 Elodesignarena
20SpaceXAI: Grok 4.61284 Elodesignarena
21Anthropic: Claude Opus 4.61283 Elodesignarena
22Google: Gemini 3.6 Flash1283 Elodesignarena
23Z.ai: GLM 5.21279 Elodesignarena
24Anthropic: Claude Haiku 5.51277 Elodesignarena
25Z.ai: GLM 5.3 Flash1273 Elodesignarena
26Anthropic: Claude Sonnet 4.61270 Elodesignarena
27Meta: Muse Spark 1.11269 Elodesignarena
28Qwen: Qwen3.7 Max1268 Elodesignarena
29SpaceXAI: Grok 4.51268 Elodesignarena
30Anthropic: Claude Sonnet 51268 Elodesignarena
31SpaceXAI: Grok 4.71267 Elodesignarena
32MoonshotAI: Kimi K2.61265 Elodesignarena
33Xiaomi: MiMo-V2.5-Pro1263 Elodesignarena
34Qwen: Qwen3.7 Plus1262 Elodesignarena
35Z.ai: GLM 5.11262 Elodesignarena
36Google: Gemini 3.5 Flash1261 Elodesignarena
37Xiaomi: MiMo-V2.51255 Elodesignarena
38Tencent: Hy41255 Elodesignarena
39Z.ai: GLM 5 Turbo1254 Elodesignarena
40Mistral: Mistral Large 41253 Elodesignarena
41OpenAI: GPT-5.51253 Elodesignarena
42Anthropic: Claude Opus 4.81249 Elodesignarena
43MoonshotAI: Kimi K2.7 Code1246 Elodesignarena
44MiniMax: MiniMax M31240 Elodesignarena
45Z.ai: GLM 51240 Elodesignarena
46Google: Gemini 3.1 Pro Preview1238 Elodesignarena
47Anthropic: Claude Opus 4.51236 Elodesignarena
48DeepSeek: DeepSeek V4 Pro 04231234 Elodesignarena
49Inception: Mercury 31232 Elodesignarena
50Reflection: Beam 1.0 501B A23B1232 Elodesignarena
51MoonshotAI: Kimi K2.51229 Elodesignarena
52Qwen: Qwen3.6 Plus1229 Elodesignarena
53MiniMax: MiniMax M2.71226 Elodesignarena
54DeepSeek: DeepSeek V4 Flash 07311223 Elodesignarena
55Z.ai: GLM 5V Turbo1221 Elodesignarena
56SpaceXAI: Grok 4.201215 Elodesignarena
57Z.ai: GLM 4.71211 Elodesignarena
58OpenAI: GPT-5.41206 Elodesignarena
59MiniMax: MiniMax M2.51201 Elodesignarena
60Thinking Machines: Inkling1200 Elodesignarena
61DeepSeek: DeepSeek V4 Flash 04231199 Elodesignarena
62MiniMax: MiniMax M2.11188 Elodesignarena
63Google: Gemini 3 Flash Preview1183 Elodesignarena
64SpaceXAI: Grok 4.31180 Elodesignarena
65Anthropic: Claude Sonnet 4.51177 Elodesignarena
66StepFun: Step 3.7 Flash1176 Elodesignarena
67Upstage: Solar Pro 41176 Elodesignarena
68Anthropic: Claude Opus 41174 Elodesignarena
69Qwen: Qwen3.5 397B A17B1173 Elodesignarena
70Z.ai: GLM 4.7 Flash1172 Elodesignarena
71Tencent: Hy31170 Elodesignarena
72DeepSeek: DeepSeek V3.1 Terminus1169 Elodesignarena
73DeepSeek: DeepSeek V3.2 Exp1165 Elodesignarena
74Anthropic: Claude Opus 4.11165 Elodesignarena
75OpenAI: GPT-5.11165 Elodesignarena
76OpenAI: GPT-5.21164 Elodesignarena
77OpenAI: GPT-51162 Elodesignarena
78Qwen: Qwen3.5 Plus 2026-02-151160 Elodesignarena
79Z.ai: GLM 4.61160 Elodesignarena
80Z.ai: GLM 4.51159 Elodesignarena
81DeepSeek: DeepSeek V3.21158 Elodesignarena
82Meta: Muse Glimmer 30B1156 Elodesignarena
83NVIDIA: Nemotron 3.5 Super VL1151 Elodesignarena
84Google: Gemini 2.5 Pro1146 Elodesignarena
85OpenAI: GPT-5.1-Codex1146 Elodesignarena
86Anthropic: Claude Sonnet 41143 Elodesignarena
87NVIDIA: Nemotron 3 Ultra1141 Elodesignarena
88OpenAI: GPT-5.3-Codex1139 Elodesignarena
89Qwen: Qwen3 Coder 480B A35B1137 Elodesignarena
90Mistral: Mistral Large 3 25121136 Elodesignarena
91Upstage: Solar Mini 41134 Elodesignarena
92MiniMax: MiniMax M21133 Elodesignarena
93DeepSeek: R1 05281132 Elodesignarena
94Z.ai: GLM 4.5 Air1130 Elodesignarena
95Arcee AI: Trinity Large Thinking1116 Elodesignarena
96Mistral: Mistral Medium 3.11115 Elodesignarena
97Qwen: Qwen3 Max1113 Elodesignarena
98OpenAI: GPT-5 Mini1109 Elodesignarena
99Anthropic: Claude Haiku 4.51109 Elodesignarena
100DeepSeek: DeepSeek V3.11106 Elodesignarena

Run your own prompt on the top 3

Muse Wonder, Claude Opus 5.5, Claude Fable 5.2, side by side on the same prompt, with each one's time and cost. A free account includes starter credit.

Compare them

Compare the leaders

More Design & Generation benchmarks

Design Arena: Website

Blind human preference for models generating a complete, styled website.

Design Arena: Game Dev

Blind human preference for models generating a playable browser game.

Design Arena: Data Viz

Blind human preference for models generating a data visualization.

Design Arena: UI Component

Blind human preference for models generating a polished UI component.

Design Arena: 3D

Blind human preference for models generating an interactive 3D scene.

Design Arena: SVG

Blind human preference for models generating an SVG illustration.

Design Arena: ASCII Art

Blind human preference for models generating ASCII art.

Design Arena: Logo

Blind human preference for models generating a logo.

Design Arena: Image

Blind human preference for models generating an image.

Design Arena: Graphic Design

Blind human preference for models generating a piece of graphic design.

Design Arena: Full-stack (agentic)

Blind human preference for models generating a full-stack app, built over multiple agentic steps.

Design Arena: Mobile Apps (agentic)

Blind human preference for models generating a mobile app, built agentically.

Design Arena: Web Apps (agentic)

Blind human preference for models generating a web app, built agentically.

Design Arena: Android Native (agentic)

Blind human preference for models generating a native Android app, built agentically.

Design Arena: PPTX Slides (agentic)

Blind human preference for models generating a PowerPoint slide deck (python-pptx), built agentically.

Design Arena: Godot Game Dev (agentic)

Blind human preference for models generating a Godot-engine game, built agentically.

Design Arena: Game Dev (agentic)

Blind human preference for models generating a game, built over multiple agentic steps.

Design Arena: HTML Slides (agentic)

Blind human preference for models generating an HTML slide deck, built agentically.

Design Arena: Slides (agentic)

Blind human preference for models generating a slide deck, built agentically.

LMArena: Text to Image

Blind human preference between models generating images from a text prompt.

LMArena: Text to Image (Photorealistic)

Blind human preference between models generating photorealistic images from a text prompt.

LMArena: Text to Image (Text Rendering)

Blind human preference between models generating images that contain written text from a text prompt.

LMArena: Text to Image (Commercial Design)

Blind human preference between models generating product shots, ads and other commercial design from a text prompt.

LMArena: Text to Image (Portraits)

Blind human preference between models generating portraits of people from a text prompt.

LMArena: Image Editing

Blind human preference between models generating edited images from an image and an instruction.

LMArena: Multi-Image Editing

Blind human preference between models generating edited images that combine several input images from several images and an instruction.

LMArena: Text to Video

Blind human preference between models generating video clips from a text prompt.

LMArena: Image to Video

Blind human preference between models generating video clips from a starting image.

Design Arena: Code is maintained by Design Arena (designarena.ai). Scores on this page are collected from openly-licensed sources and each links to its origin. See the full matrix to compare every model across every benchmark.