---
title: "Web dev leaderboard"
description: "Rankings on building a working web page from a one-sentence request."
canonical: https://pirouter.ai/rankings/webdev
last-updated: 2026-10-15
---

# Web dev leaderboard

> Rankings on building a working web page from a one-sentence request.

- Updated: 2026-10-01
- 1,014,328 votes · 121 models
- Score · higher is better

## Full ranking

| Rank | Rank spread | Model | Vendor | Score | Votes |
|---|---|---|---|---|---|
| 1 | 1–2 | [Claude Opus 5.5 \(max\)](https://pirouter.ai/models/anthropic/claude-opus-5.5) | Anthropic | 1815 ±16 | 2062 |
| 2 | 2–3 | [GPT-6 Astra \(max\)](https://pirouter.ai/models/openai/gpt-6-astra) | OpenAI | 1788 ±10 | 6123 |
| 3 | 1–4 | [Claude Sonnet 5.5 \(xhigh\)](https://pirouter.ai/models/anthropic/claude-sonnet-5.5) | Anthropic | 1786 ±18 | 1531 |
| 4 | 3–5 | [GPT-6.1 Sol \(max\)](https://pirouter.ai/models/openai/gpt-6.1-sol) | OpenAI | 1758 ±17 | 1620 |
| 5 | 4–5 | [Claude Fable 5.1 \(max\)](https://pirouter.ai/models/anthropic/claude-fable-5.1) | Anthropic | 1749 ±10 | 6318 |
| 6 | 6–8 | Claude Opus 5 (max) | Anthropic | 1695 ±7 | 16954 |
| 7 | 6–10 | [GPT-6 Sol \(max\)](https://pirouter.ai/models/openai/gpt-6-sol) | OpenAI | 1689 ±11 | 3411 |
| 8 | 6–10 | Gemini 4 Argon (high) | Google | 1680 ±13 | 2422 |
| 9 | 7–12 | Qwen3.8 (max) | Alibaba | 1671 ±12 | 3454 |
| 10 | 7–12 | Qwen3.8 Max 0902 | Alibaba | 1670 ±8 | 9485 |
| 11 | 9–12 | Kimi K3 (max) | Moonshot | 1658 ±6 | 16513 |
| 12 | 9–13 | Muse Spark 1.3 (max) | Meta | 1657 ±9 | 7249 |
| 13 | 12–21 | Grok 4.7 (xhigh) | xAI | 1638 ±12 | 3216 |
| 14 | 13–19 | Qwen3.8 Flash Next | Alibaba | 1638 ±9 | 6193 |
| 15 | 13–21 | Hy4 Preview | Tencent | 1633 ±9 | 5088 |
| 16 | 13–22 | Claude Fable 5 (high) | Anthropic | 1625 ±6 | 14126 |
| 17 | 13–22 | GLM 5.3 (max) | Z.ai | 1623 ±8 | 7658 |
| 18 | 13–23 | [DeepSeek V4.1 Flash \(max\)](https://pirouter.ai/models/deepseek/deepseek-v4.1-flash) | DeepSeek | 1620 ±10 | 3960 |
| 19 | 14–22 | [GPT-5.6 Sol \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-sol) | OpenAI | 1620 ±6 | 17128 |
| 20 | 14–22 | Grok 4.6 (high) | xAI | 1620 ±8 | 8315 |
| 21 | 13–23 | MiMo V2.6 Pro | Xiaomi | 1618 ±12 | 2734 |
| 22 | 16–23 | [GLM 5.3 Flash](https://pirouter.ai/models/z-ai/glm-5.3-flash) | Z.ai | 1616 ±8 | 10355 |
| 23 | 20–24 | [GLM 5.2 \(max\)](https://pirouter.ai/models/z-ai/glm-5.2) | Z.ai | 1605 ±6 | 14729 |
| 24 | 23–29 | [Gemini 3.7 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.7-flash) | Google | 1592 ±7 | 9624 |
| 25 | 24–29 | Qwen3.8 27b | Alibaba | 1591 ±7 | 12388 |
| 26 | 24–30 | [Gemini 3.8 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.8-flash) | Google | 1583 ±8 | 8524 |
| 27 | 24–30 | [DeepSeek V4 Pro 0813 \(high\)](https://pirouter.ai/models/deepseek/deepseek-v4-pro) | DeepSeek | 1583 ±9 | 4882 |
| 28 | 24–30 | [DeepSeek V4 Flash 0731 \(high\)](https://pirouter.ai/models/deepseek/deepseek-v4-flash) | DeepSeek | 1581 ±9 | 5040 |
| 29 | 24–30 | [GPT-6 Luna \(max\)](https://pirouter.ai/models/openai/gpt-6-luna) | OpenAI | 1579 ±9 | 6429 |
| 30 | 26–33 | Step 5 Preview (high) | StepFun | 1570 ±13 | 2506 |
| 31 | 30–33 | Claude Opus 4.7 (high) | Anthropic | 1557 ±6 | 17982 |
| 32 | 30–34 | Claude Opus 4.8 (high) | Anthropic | 1556 ±6 | 18908 |
| 33 | 30–37 | Grok 4.5 | xAI | 1552 ±7 | 11393 |
| 34 | 32–38 | Claude Opus 4.6 (high) | Anthropic | 1546 ±5 | 19519 |
| 35 | 33–38 | Muse Spark 1.1 | Meta | 1542 ±8 | 8070 |
| 36 | 33–38 | [Claude Sonnet 5 \(high\)](https://pirouter.ai/models/anthropic/claude-sonnet-5) | Anthropic | 1539 ±6 | 14130 |
| 37 | 34–38 | [Gemini 3.6 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.6-flash) | Google | 1536 ±7 | 8823 |
| 38 | 33–44 | Muse Spark 1.2 (xhigh) | Meta | 1532 ±14 | 2183 |
| 39 | 38–44 | Claude Sonnet 4.6 | Anthropic | 1521 ±5 | 22960 |
| 40 | 38–47 | [GPT-5.6 Terra \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-terra) | OpenAI | 1519 ±7 | 12526 |
| 41 | 38–47 | [GPT-5.6 Luna \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.6-luna) | OpenAI | 1518 ±6 | 12776 |
| 42 | 38–47 | [Seed 2.1 Pro](https://pirouter.ai/models/bytedance/seed-2.1-pro) | ByteDance | 1517 ±6 | 13312 |
| 43 | 38–47 | Qwen3.7 (max) | Alibaba | 1515 ±7 | 8922 |
| 44 | 38–47 | [GPT-5.5 \(xhigh\)](https://pirouter.ai/models/openai/gpt-5.5) | OpenAI | 1512 ±6 | 15873 |
| 45 | 40–48 | Kimi K2.6 | Moonshot | 1509 ±7 | 10208 |
| 46 | 40–48 | GLM 5.1 | Z.ai | 1509 ±7 | 10797 |
| 47 | 40–49 | Hy3 | Tencent | 1507 ±9 | 5802 |
| 48 | 45–50 | [Gemini 3.5 Flash \(high\)](https://pirouter.ai/models/google/gemini-3.5-flash) | Google | 1499 ±7 | 9497 |
| 49 | 47–51 | Claude Opus 4.5 20251101 High 32k | Anthropic | 1493 ±8 | 11034 |
| 50 | 49–55 | Minimax M3 | MiniMax | 1482 ±6 | 17613 |
| 51 | 48–56 | Qwen3.6 Preview (max) | Alibaba | 1482 ±13 | 2716 |
| 52 | 50–56 | MiMo V2.5 Pro | Xiaomi | 1478 ±5 | 20313 |
| 53 | 50–57 | Kimi K2.7 Code | Moonshot | 1473 ±9 | 4993 |
| 54 | 51–57 | Claude Opus 4.5 | Anthropic | 1469 ±7 | 13427 |
| 55 | 50–61 | [GPT-5.4 \(high\)](https://pirouter.ai/models/openai/gpt-5.4) | OpenAI | 1465 ±19 | 1351 |
| 56 | 53–57 | Qwen3.6 Plus | Alibaba | 1461 ±6 | 18688 |
| 57 | 56–63 | Gemini 3.1 Pro Preview | Google | 1446 ±5 | 24347 |
| 58 | 50–78 | [Gemini 3.5 Flash Lite](https://pirouter.ai/models/google/gemini-3.5-flash-lite) | Google | 1440 ±41 | 242 |
| 59 | 56–67 | Gemini 3 Pro | Google | 1439 ±8 | 14092 |
| 60 | 56–67 | Gemini 3 Flash | Google | 1439 ±9 | 10896 |
| 61 | 57–67 | MiMo V2.5 | Xiaomi | 1438 ±6 | 15018 |
| 62 | 58–67 | Kimi K2.5 (thinking) | Moonshot | 1436 ±5 | 20149 |
| 63 | 56–67 | GLM 4.7 | Z.ai | 1435 ±12 | 4007 |
| 64 | 57–67 | GLM 5 | Z.ai | 1434 ±8 | 7504 |
| 65 | 58–67 | MiMo V2 Pro | Xiaomi | 1433 ±8 | 7253 |
| 66 | 58–76 | GPT-5 (medium) | OpenAI | 1417 ±16 | 3091 |
| 67 | 58–80 | GPT-5.2 | OpenAI | 1416 ±22 | 1082 |
| 68 | 65–73 | Inkling | Thinky | 1413 ±6 | 13705 |
| 69 | 65–78 | Inkling Small | Thinky | 1408 ±9 | 5421 |
| 70 | 65–79 | GPT-5.3 Codex | OpenAI | 1408 ±14 | 2643 |
| 71 | 65–80 | Kimi K2.5 Instant | Moonshot | 1404 ±12 | 3271 |
| 72 | 65–82 | GLM 5v Turbo | Z.ai | 1400 ±13 | 2416 |
| 73 | 66–79 | Qwen3.5 397b A17b | Alibaba | 1399 ±5 | 21280 |
| 74 | 66–81 | [GPT-5.4 Mini \(high\)](https://pirouter.ai/models/openai/gpt-5.4-mini) | OpenAI | 1397 ±7 | 11998 |
| 75 | 66–81 | Minimax M2.7 | MiniMax | 1397 ±6 | 16074 |
| 76 | 65–82 | GPT-5.1 (medium) | OpenAI | 1395 ±12 | 4911 |
| 77 | 67–82 | Claude Sonnet 4.5 20250929 High 32k | Anthropic | 1393 ±8 | 13253 |
| 78 | 67–84 | Claude Opus 4.1 | Anthropic | 1389 ±11 | 6926 |
| 79 | 69–84 | Minimax M2.5 | MiniMax | 1386 ±8 | 7637 |
| 80 | 73–84 | Claude Sonnet 4.5 | Anthropic | 1384 ±7 | 15722 |
| 81 | 75–84 | Gemini 3 Flash | Google | 1384 ±5 | 22213 |
| 82 | 71–85 | Minimax M2.1 Preview | MiniMax | 1384 ±10 | 7644 |
| 83 | 78–89 | Grok 4.20 Beta 0309 Reasoning | xAI | 1374 ±6 | 15503 |
| 84 | 78–92 | Solar Pro4 | Upstage | 1370 ±10 | 4945 |
| 85 | 83–92 | Gemma 4 31b | Google | 1365 ±6 | 13325 |
| 86 | 83–93 | DeepSeek V3.2 (thinking) | DeepSeek | 1362 ±9 | 6921 |
| 87 | 84–93 | Qwen3.5 122b A10b | Alibaba | 1360 ±8 | 8249 |
| 88 | 82–96 | Gemma 4 26b A4b | Google | 1359 ±17 | 1502 |
| 89 | 84–94 | Qwen3.5 27b | Alibaba | 1357 ±8 | 7794 |
| 90 | 84–93 | Grok 4.3 | xAI | 1357 ±6 | 15057 |
| 91 | 83–97 | Hunyuan Hy3 Preview | Tencent | 1356 ±17 | 1455 |
| 92 | 83–97 | Muse Glimmer | Meta | 1355 ±16 | 1663 |
| 93 | 86–97 | Laguna M.1 | Poolside | 1348 ±9 | 5418 |
| 94 | 89–99 | GLM 4.6 | Z.ai | 1339 ±11 | 6780 |
| 95 | 90–98 | GPT-5.2 Codex | OpenAI | 1339 ±9 | 6722 |
| 96 | 90–99 | GPT-5.1 Codex | OpenAI | 1337 ±12 | 5005 |
| 97 | 91–99 | MiMo V2 Flash | Xiaomi | 1330 ±10 | 5692 |
| 98 | 94–99 | Claude Haiku 4.5 | Anthropic | 1329 ±5 | 29184 |
| 99 | 95–99 | Kimi K2 Thinking Turbo | Moonshot | 1321 ±7 | 13093 |
| 100 | 100–102 | Laguna Xs.2 | Poolside | 1302 ±11 | 4256 |

## FAQ

### What is the best AI model for web dev?

As of 2026-10-01, Anthropic Claude Opus 5.5 (max) is #1 on the web dev board with a score of 1815, rank spread 1–2.

### What is the best open-weights model for web dev?

Kimi K3 (Moonshot), #11 on this board.

### What does this board rank?

Rankings on building a working web page from a one-sentence request.

### How often is it updated?

Whenever new models ship or the rankings change; this board was last updated on 2026-10-01.

Data: [LMArena leaderboard dataset](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset), used under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/); filtered and reasoning tiers merged, scores unchanged.
View the original board: https://arena.ai/leaderboard/code