Coding · Elo
LMArena WebDev
Arena where two models each build a web app from the same prompt and users vote on the result.
Active Contamination risk: Low 141 results · 127 models Updated Oct 22, 2026 Newest result: 2026-10-08 Official leaderboard ↗
What it measures
Human preference for generated web apps (front-end coding).
Limitations
Visual polish can outweigh code quality; same preference biases as the text arena.
Contamination risk: Low
Prompts are live user requests.
Leaderboard
Top 100 of 127
| # | Model | Provider | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|---|---|
| 1 | claude-opus-5.5-max | Anthropic | 1813 | 1 | Overall; 2294 votes; 95% CI 1798–1828 | Official leaderboard | Oct 8, 2026 |
| 2 | gpt-6-astra-max | OpenAI | 1786 | 2 | Overall; 5189 votes; 95% CI 1775–1797 | Official leaderboard | Oct 8, 2026 |
| 3 | Claude Sonnet 5.5 | Anthropic | 1774 | 3 | Overall; 2323 votes; 95% CI 1759–1789“claude-sonnet-5.5-xhigh” | Official leaderboard | Oct 8, 2026 |
| 4 | gpt-6.1-sol-max | OpenAI | 1755 | 4 | Overall; 2102 votes; 95% CI 1740–1770 | Official leaderboard | Oct 8, 2026 |
| 5 | claude-fable-5.1-max | Anthropic | 1744 | 5 | Overall; 6663 votes; 95% CI 1734–1753 | Official leaderboard | Oct 8, 2026 |
| 6 | claude-opus-5-max | Anthropic | 1691 | 7 | Overall; 17320 votes; 95% CI 1685–1698 | Official leaderboard | Oct 8, 2026 |
| 7 | gpt-6-sol-max | OpenAI | 1688 | 8 | Overall; 3407 votes; 95% CI 1676–1700 | Official leaderboard | Oct 8, 2026 |
| 8 | Gemini 4 Argon | 1678 | 9 | Overall; 1771 votes; 95% CI 1662–1693“gemini-4-argon-high” | Official leaderboard | Oct 8, 2026 | |
| 9 | Qwen3.8 Max (0902) | Alibaba (Qwen) | 1674 | 10 | Overall; 11182 votes; 95% CI 1666–1681“qwen3.8-max-0902” | Official leaderboard | Oct 8, 2026 |
| 10 | Qwen 3.8 Max | Alibaba (Qwen) | 1672 | 11 | Overall; 3446 votes; 95% CI 1660–1684“qwen3.8-max” | Official leaderboard | Oct 8, 2026 |
| 11 | Claude Opus 5 | Anthropic | 1657 | 12 | Overall; 22340 votes; 95% CI 1651–1662“claude-opus-5-high” | Official leaderboard | Oct 8, 2026 |
| 12 | muse-spark-1.3-max | Meta | 1657 | 13 | Overall; 7886 votes; 95% CI 1649–1665 | Official leaderboard | Oct 8, 2026 |
| 13 | kimi-k3-maxOW | Moonshot AI | 1654 | 14 | Overall; 17412 votes; 95% CI 1648–1661 | Official leaderboard | Oct 8, 2026 |
| 14 | Grok 4.7 | xAI | 1639 | 15 | Overall; 3936 votes; 95% CI 1628–1650“grok-4.7-xhigh” | Official leaderboard | Oct 8, 2026 |
| 15 | MiMo-V2.6 FlashOW | Xiaomi Corp | 1637 | 16 | Overall; 4058 votes; 95% CI 1626–1647“mimo-v2.6-flash” | Official leaderboard | Oct 8, 2026 |
| 16 | qwen3.8-flash-nextOW | Alibaba (Qwen) | 1633 | 17 | Overall; 6932 votes; 95% CI 1624–1641 | Official leaderboard | Oct 8, 2026 |
| 17 | hy4-previewOW | Tencent | 1632 | 18 | Overall; 4792 votes; 95% CI 1622–1641 | Official leaderboard | Oct 8, 2026 |
| 18 | MiMo-V2.6 ProOW | Xiaomi Corp | 1629 | 19 | Overall; 3649 votes; 95% CI 1618–1640“mimo-v2.6-pro” | Official leaderboard | Oct 8, 2026 |
| 19 | Muse Spark 1.3 | Meta | 1626 | 20 | Overall; 7123 votes; 95% CI 1617–1634“muse-spark-1.3 (xHigh)” | Official leaderboard | Oct 8, 2026 |
| 20 | Claude Fable 5 | Anthropic | 1625 | 21 | Overall; 14657 votes; 95% CI 1618–1631“claude-fable-5-high” | Official leaderboard | Oct 8, 2026 |
| 21 | glm-5.3-maxOW | Zhipu AI (Z.ai) | 1622 | 22 | Overall; 8382 votes; 95% CI 1614–1630 | Official leaderboard | Oct 8, 2026 |
| 22 | deepseek-v4.1-flash-maxOW | DeepSeek | 1619 | 23 | Overall; 3542 votes; 95% CI 1608–1630 | Official leaderboard | Oct 8, 2026 |
| 23 | gpt-5.6-sol-xhigh (codex-harness) | OpenAI | 1618 | 24 | Overall; 16639 votes; 95% CI 1612–1624 | Official leaderboard | Oct 8, 2026 |
| 24 | Grok 4.6 | xAI | 1617 | 25 | Overall; 8958 votes; 95% CI 1609–1625“grok-4.6-high” | Official leaderboard | Oct 8, 2026 |
| 25 | GLM-5.3-FlashOW | Zhipu AI (Z.ai) | 1609 | 26 | Overall; 13697 votes; 95% CI 1602–1616“glm-5.3-flash” | Official leaderboard | Oct 8, 2026 |
| 26 | glm-5.2-maxOW | Zhipu AI (Z.ai) | 1603 | 27 | Overall; 15351 votes; 95% CI 1597–1609 | Official leaderboard | Oct 8, 2026 |
| 27 | Qwen 3.8 27BOW | Alibaba (Qwen) | 1593 | 28 | Overall; 13777 votes; 95% CI 1586–1600“qwen3.8-27b” | Official leaderboard | Oct 8, 2026 |
| 28 | Gemini 3.7 Flash | 1592 | 29 | Overall; 10637 votes; 95% CI 1584–1599“gemini-3.7-flash-high” | Official leaderboard | Oct 8, 2026 | |
| 29 | Claude Haiku 5.5 | Anthropic | 1587 | 30 | Overall; 978 votes; 95% CI 1567–1607“claude-haiku-5.5-high” | Official leaderboard | Oct 8, 2026 |
| 30 | Gemini 3.8 Flash | 1584 | 31 | Overall; 9225 votes; 95% CI 1576–1591“gemini-3.8-flash-high” | Official leaderboard | Oct 8, 2026 | |
| 31 | DeepSeek-V4-ProOW | DeepSeek | 1582 | 32 | Overall; 4740 votes; 95% CI 1573–1591“deepseek-v4-pro-high-20260813” | Official leaderboard | Oct 8, 2026 |
| 32 | deepseek-v4-flashOW | DeepSeek | 1582 | 33 | Overall; 4974 votes; 95% CI 1572–1591“deepseek-v4-flash-high” | Official leaderboard | Oct 8, 2026 |
| 33 | gpt-6-luna-max | OpenAI | 1581 | 34 | Overall; 12332 votes; 95% CI 1574–1588 | Official leaderboard | Oct 8, 2026 |
| 34 | Step 5 Preview | StepFun | 1564 | 35 | Overall; 3351 votes; 95% CI 1552–1575“step-5-preview-high” | Official leaderboard | Oct 8, 2026 |
| 35 | Claude Opus 4.7 | Anthropic | 1558 | 36 | Overall; 17956 votes; 95% CI 1552–1563“claude-opus-4-7-high” | Official leaderboard | Oct 8, 2026 |
| 36 | Claude Opus 4.8 | Anthropic | 1556 | 37 | Overall; 18534 votes; 95% CI 1550–1562“claude-opus-4-8-high” | Official leaderboard | Oct 8, 2026 |
| 37 | Grok 4.5 | xAI | 1553 | 39 | Overall; 11116 votes; 95% CI 1546–1560“grok-4.5” | Official leaderboard | Oct 8, 2026 |
| 38 | Claude Opus 4.6 | Anthropic | 1547 | 40 | Overall; 19434 votes; 95% CI 1541–1552“claude-opus-4-6-high” | Official leaderboard | Oct 8, 2026 |
| 39 | Muse Spark 1.1 | Meta | 1542 | 41 | Overall; 8002 votes; 95% CI 1535–1550“muse-spark-1.1” | Official leaderboard | Oct 8, 2026 |
| 40 | Mistral Large 4 | Mistral AI | 1541 | 42 | Overall; 1478 votes; 95% CI 1525–1558“mistral-large-4” | Official leaderboard | Oct 8, 2026 |
| 41 | Claude Sonnet 5 | Anthropic | 1541 | 43 | Overall; 14574 votes; 95% CI 1535–1547“claude-sonnet-5-high” | Official leaderboard | Oct 8, 2026 |
| 42 | Gemini 3.6 Flash | 1538 | 44 | Overall; 8766 votes; 95% CI 1530–1545“gemini-3.6-flash-high” | Official leaderboard | Oct 8, 2026 | |
| 43 | muse-spark-1.2 (xHigh) | Meta | 1533 | 47 | Overall; 2171 votes; 95% CI 1519–1546 | Official leaderboard | Oct 8, 2026 |
| 44 | Claude Sonnet 4.6 | Anthropic | 1522 | 48 | Overall; 22866 votes; 95% CI 1517–1528“claude-sonnet-4-6” | Official leaderboard | Oct 8, 2026 |
| 45 | gpt-5.6-terra-xhigh (codex-harness) | OpenAI | 1522 | 49 | Overall; 12367 votes; 95% CI 1515–1528 | Official leaderboard | Oct 8, 2026 |
| 46 | seed-2.1-pro-preview | ByteDance | 1519 | 50 | Overall; 13897 votes; 95% CI 1513–1525 | Official leaderboard | Oct 8, 2026 |
| 47 | gpt-5.6-luna-xhigh (codex-harness) | OpenAI | 1519 | 51 | Overall; 12556 votes; 95% CI 1513–1525 | Official leaderboard | Oct 8, 2026 |
| 48 | Qwen3.7-Max | Alibaba (Qwen) | 1515 | 52 | Overall; 8905 votes; 95% CI 1508–1522“qwen3.7-max-20260517” | Official leaderboard | Oct 8, 2026 |
| 49 | gpt-5.5-xhigh (codex-harness) | OpenAI | 1513 | 53 | Overall; 15698 votes; 95% CI 1507–1519 | Official leaderboard | Oct 8, 2026 |
| 50 | Kimi K2.6OW | Moonshot AI | 1509 | 54 | Overall; 10187 votes; 95% CI 1502–1516“kimi-k2.6” | Official leaderboard | Oct 8, 2026 |
| 51 | hy3OW | Tencent | 1508 | 55 | Overall; 5660 votes; 95% CI 1500–1517 | Official leaderboard | Oct 8, 2026 |
| 52 | GLM-5.1OW | Zhipu AI (Z.ai) | 1508 | 56 | Overall; 10739 votes; 95% CI 1502–1515“glm-5.1” | Official leaderboard | Oct 8, 2026 |
| 53 | Gemini 3.5 Flash | 1499 | 57 | Overall; 9415 votes; 95% CI 1492–1506“gemini-3.5-flash-high” | Official leaderboard | Oct 8, 2026 | |
| 54 | Claude Opus 4.5 | Anthropic | 1494 | 58 | Overall; 11034 votes; 95% CI 1486–1502“claude-opus-4-5-20251101-high-32k” | Official leaderboard | Oct 8, 2026 |
| 55 | gpt-5.5-high (codex-harness) | OpenAI | 1487 | 60 | Overall; 18002 votes; 95% CI 1482–1493 | Official leaderboard | Oct 8, 2026 |
| 56 | Qwen 3.6 Max (Preview) | Alibaba (Qwen) | 1482 | 61 | Overall; 2708 votes; 95% CI 1470–1495“qwen3.6-max-preview” | Official leaderboard | Oct 8, 2026 |
| 57 | MiniMax-M3OW | MiniMax | 1482 | 62 | Overall; 18288 votes; 95% CI 1476–1487“minimax-m3” | Official leaderboard | Oct 8, 2026 |
| 58 | MiMo-V2.5-ProOW | Xiaomi Corp | 1479 | 63 | Overall; 21036 votes; 95% CI 1474–1485“mimo-v2.5-pro” | Official leaderboard | Oct 8, 2026 |
| 59 | Kimi K2.7 CodeOW | Moonshot AI | 1473 | 64 | Overall; 4987 votes; 95% CI 1464–1483“kimi-k2.7-code” | Official leaderboard | Oct 8, 2026 |
| 60 | gpt-5.4-high (codex-harness) | OpenAI | 1465 | 66 | Overall; 1350 votes; 95% CI 1446–1484 | Official leaderboard | Oct 8, 2026 |
| 61 | deepseek-v4-pro-high-previewOW | DeepSeek | 1464 | 67 | Overall; 13194 votes; 95% CI 1457–1470 | Official leaderboard | Oct 8, 2026 |
| 62 | Qwen 3.6 Plus | Alibaba (Qwen) | 1461 | 68 | Overall; 18621 votes; 95% CI 1456–1467“qwen3.6-plus” | Official leaderboard | Oct 8, 2026 |
| 63 | gpt-5.5 (codex-harness) | OpenAI | 1456 | 69 | Overall; 15911 votes; 95% CI 1450–1462 | Official leaderboard | Oct 8, 2026 |
| 64 | Gemini 3.1 Pro | 1447 | 71 | Overall; 24249 votes; 95% CI 1442–1452“gemini-3.1-pro-preview” | Official leaderboard | Oct 8, 2026 | |
| 65 | gpt-5.4-medium (codex-harness) | OpenAI | 1444 | 72 | Overall; 1376 votes; 95% CI 1426–1463 | Official leaderboard | Oct 8, 2026 |
| 66 | Gemini 3.5 Flash-Lite | 1440 | 73 | Overall; 242 votes; 95% CI 1399–1480“gemini-3.5-flash-lite” | Official leaderboard | Oct 8, 2026 | |
| 67 | Gemini 3 Pro | 1440 | 74 | Overall; 14090 votes; 95% CI 1431–1448“gemini-3-pro” | Official leaderboard | Oct 8, 2026 | |
| 68 | Gemini 3 Flash | 1439 | 75 | Overall; 10894 votes; 95% CI 1431–1448“gemini-3-flash” | Official leaderboard | Oct 8, 2026 | |
| 69 | MiMo-V2.5OW | Xiaomi Corp | 1438 | 76 | Overall; 14947 votes; 95% CI 1432–1444“mimo-v2.5” | Official leaderboard | Oct 8, 2026 |
| 70 | Kimi K2.5OW | Moonshot AI | 1437 | 77 | Overall; 20127 votes; 95% CI 1431–1442“kimi-k2.5-thinking” | Official leaderboard | Oct 8, 2026 |
| 71 | GLM-4.7OW | Zhipu AI (Z.ai) | 1435 | 78 | Overall; 4007 votes; 95% CI 1423–1447“glm-4.7” | Official leaderboard | Oct 8, 2026 |
| 72 | GLM-5OW | Zhipu AI (Z.ai) | 1434 | 79 | Overall; 7506 votes; 95% CI 1426–1443“glm-5” | Official leaderboard | Oct 8, 2026 |
| 73 | MiMo-V2-Pro | Xiaomi Corp | 1433 | 80 | Overall; 7244 votes; 95% CI 1425–1441“mimo-v2-pro” | Official leaderboard | Oct 8, 2026 |
| 74 | deepseek-v4-flash-high-previewOW | DeepSeek | 1431 | 81 | Overall; 10144 votes; 95% CI 1424–1438 | Official leaderboard | Oct 8, 2026 |
| 75 | GPT-5 | OpenAI | 1418 | 82 | Overall; 3092 votes; 95% CI 1402–1433“gpt-5-medium” | Official leaderboard | Oct 8, 2026 |
| 76 | GPT-5.2 | OpenAI | 1416 | 83 | Overall; 1082 votes; 95% CI 1394–1438“gpt-5.2” | Official leaderboard | Oct 8, 2026 |
| 77 | InklingOW | Thinking Machines | 1413 | 84 | Overall; 14358 votes; 95% CI 1407–1419“inkling” | Official leaderboard | Oct 8, 2026 |
| 78 | Inkling-SmallOW | Thinking Machines | 1409 | 85 | Overall; 5368 votes; 95% CI 1400–1418“Inkling Small” | Official leaderboard | Oct 8, 2026 |
| 79 | gpt-5.3-codex (codex-harness) | OpenAI | 1409 | 86 | Overall; 2643 votes; 95% CI 1395–1422 | Official leaderboard | Oct 8, 2026 |
| 80 | glm-5v-turbo | Zhipu AI (Z.ai) | 1401 | 88 | Overall; 2411 votes; 95% CI 1388–1414 | Official leaderboard | Oct 8, 2026 |
| 81 | GPT-5.4 | OpenAI | 1400 | 89 | Overall; 3734 votes; 95% CI 1390–1411“gpt-5.4” | Official leaderboard | Oct 8, 2026 |
| 82 | Qwen3.5 397B-A17BOW | Alibaba (Qwen) | 1400 | 90 | Overall; 21189 votes; 95% CI 1395–1405“qwen3.5-397b-a17b” | Official leaderboard | Oct 8, 2026 |
| 83 | MiniMax-M2.7OW | MiniMax | 1398 | 91 | Overall; 16011 votes; 95% CI 1392–1404“minimax-m2.7” | Official leaderboard | Oct 8, 2026 |
| 84 | GPT-5.4 Mini | OpenAI | 1397 | 92 | Overall; 11976 votes; 95% CI 1391–1404“gpt-5.4-mini-high” | Official leaderboard | Oct 8, 2026 |
| 85 | GPT-5.1 | OpenAI | 1395 | 93 | Overall; 4912 votes; 95% CI 1384–1407“gpt-5.1-medium” | Official leaderboard | Oct 8, 2026 |
| 86 | Claude Sonnet 4.5 | Anthropic | 1393 | 94 | Overall; 13256 votes; 95% CI 1386–1401“claude-sonnet-4-5-20250929-high-32k” | Official leaderboard | Oct 8, 2026 |
| 87 | Claude Opus 4.1 | Anthropic | 1390 | 95 | Overall; 6926 votes; 95% CI 1379–1401“claude-opus-4-1-20250805” | Official leaderboard | Oct 8, 2026 |
| 88 | MiniMax-M2.5OW | MiniMax | 1387 | 96 | Overall; 7635 votes; 95% CI 1378–1395“minimax-m2.5” | Official leaderboard | Oct 8, 2026 |
| 89 | minimax-m2.1-previewOW | MiniMax | 1384 | 99 | Overall; 7645 votes; 95% CI 1375–1394 | Official leaderboard | Oct 8, 2026 |
| 90 | grok-4.20-beta-0309-reasoning | xAI | 1375 | 100 | Overall; 15474 votes; 95% CI 1369–1381 | Official leaderboard | Oct 8, 2026 |
| 91 | solar-pro4 | upstage | 1371 | 102 | Overall; 4668 votes; 95% CI 1361–1381 | Official leaderboard | Oct 8, 2026 |
| 92 | gemma-4-31bOW | 1366 | 103 | Overall; 13718 votes; 95% CI 1360–1372 | Official leaderboard | Oct 8, 2026 | |
| 93 | DeepSeek-V3.2OW | DeepSeek | 1362 | 104 | Overall; 6921 votes; 95% CI 1353–1371“deepseek-v3.2-thinking” | Official leaderboard | Oct 8, 2026 |
| 94 | Qwen3.5-122B-A10BOW | Alibaba (Qwen) | 1360 | 105 | Overall; 8241 votes; 95% CI 1353–1368“qwen3.5-122b-a10b” | Official leaderboard | Oct 8, 2026 |
| 95 | Gemma 4 26B A4BOW | 1359 | 106 | Overall; 1502 votes; 95% CI 1342–1376“gemma-4-26b-a4b” | Official leaderboard | Oct 8, 2026 | |
| 96 | Qwen3.5-27BOW | Alibaba (Qwen) | 1358 | 107 | Overall; 7784 votes; 95% CI 1350–1366“qwen3.5-27b” | Official leaderboard | Oct 8, 2026 |
| 97 | Grok 4.3 Beta | xAI | 1357 | 108 | Overall; 14994 votes; 95% CI 1351–1363“grok-4.3” | Official leaderboard | Oct 8, 2026 |
| 98 | hunyuan-hy3-previewOW | Tencent | 1355 | 109 | Overall; 1448 votes; 95% CI 1338–1373 | Official leaderboard | Oct 8, 2026 |
| 99 | muse-glimmerOW | Meta | 1355 | 110 | Overall; 1659 votes; 95% CI 1339–1371 | Official leaderboard | Oct 8, 2026 |
| 100 | Laguna M.1OW | Poolside | 1349 | 111 | Overall; 5418 votes; 95% CI 1339–1358“laguna-m.1” | Official leaderboard | Oct 8, 2026 |
Data sources & licences
| Source | Licence / terms | How we reuse it | Last fetched |
|---|---|---|---|
| LMArena leaderboard dataset LMArena, Arena Leaderboard Dataset (Hugging Face), CC BY 4.0 | CC BY 4.0 | Open licence – full data with attribution | Oct 10, 2026 ⚠︎ |
FAQ
What does LMArena WebDev measure?
Arena where two models each build a web app from the same prompt and users vote on the result. Human preference for generated web apps (front-end coding).
How reliable is LMArena WebDev?
Visual polish can outweigh code quality; same preference biases as the text arena. Contamination risk: Low – Prompts are live user requests.