Noometry

Coding benchmark

LMArena WebDev leaderboard

As of October 2026, Claude Opus 5.5 has the highest published LMArena WebDev score on Noometry at 1813, out of 113 models with results.

Last verified

About LMArena WebDev

Blind votes on web apps built by two anonymous models from the same prompt.

Category
Coding
Introduced
2024
Format
Pairwise human votes
Unit
Arena rating (Bradley–Terry)
Official site
lmarena.ai

Top 15 models

  1. Claude Opus 5.5 1813
  2. GPT-6 Astra 1786
  3. Claude Sonnet 5.5 1774
  4. GPT-6.1 Sol 1755
  5. Claude Fable 5.1 1744
  6. Claude Opus 5 1691
  7. GPT-6 Sol 1688
  8. Gemini 4 Argon 1678
  9. Qwen3.8 Max 1674
  10. Muse Spark 1.3 1657
  11. Kimi K3 1654
  12. Grok 4.7 1639
  13. MiMo-V2.6-Flash 1637
  14. Hy4 preview 1632
  15. MiMo-V2.6-Pro 1629

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderRatingSettingSourceDate
1Claude Opus 5.5 Anthropic1813LMArena2026-10-08
2GPT-6 Astra OpenAI1786LMArena2026-10-08
3Claude Sonnet 5.5 Anthropic1774xhighLMArena2026-10-08
4GPT-6.1 Sol OpenAI1755LMArena2026-10-08
5Claude Fable 5.1 Anthropic1744LMArena2026-10-08
6Claude Opus 5 Anthropic1691LMArena2026-10-08
7GPT-6 Sol OpenAI1688LMArena2026-10-08
8Gemini 4 Argon Google1678highLMArena2026-10-08
9Qwen3.8 Max Alibaba (Qwen)1674LMArena2026-10-08
10Muse Spark 1.3 Meta1657LMArena2026-10-08
11Kimi K3 Moonshot AI1654LMArena2026-10-08
12Grok 4.7 xAI1639xhighLMArena2026-10-08
13MiMo-V2.6-Flash Xiaomi1637LMArena2026-10-08
14Hy4 preview Tencent1632LMArena2026-10-08
15MiMo-V2.6-Pro Xiaomi1629LMArena2026-10-08
16Claude Fable 5 Anthropic1625highLMArena2026-10-08
17GLM-5.3 Z.ai (Zhipu)1622LMArena2026-10-08
18DeepSeek V4.1 Flash DeepSeek1619LMArena2026-10-08
19GPT-5.6 Sol OpenAI1618LMArena2026-10-08
20Grok 4.6 xAI1617highLMArena2026-10-08
21GLM-5.3-Flash Z.ai (Zhipu)1609LMArena2026-10-08
22GLM-5.2 Z.ai (Zhipu)1603LMArena2026-10-08
23Qwen3.8 27B Alibaba (Qwen)1593LMArena2026-10-08
24Gemini 3.7 Flash Google1592highLMArena2026-10-08
25Claude Haiku 5.5 Anthropic1587highLMArena2026-10-08
26Gemini 3.8 Flash Google1584highLMArena2026-10-08
27DeepSeek V4 Pro DeepSeek1582LMArena2026-10-08
28DeepSeek V4 Flash DeepSeek1582highLMArena2026-10-08
29GPT-6 Luna OpenAI1581LMArena2026-10-08
30Step 5 Preview StepFun1564highLMArena2026-10-08
31Claude Opus 4.7 Anthropic1558highLMArena2026-10-08
32Claude Opus 4.8 Anthropic1556highLMArena2026-10-08
33Grok 4.5 xAI1553LMArena2026-10-08
34Claude Opus 4.6 Anthropic1547highLMArena2026-10-08
35Muse Spark 1.1 Meta1542LMArena2026-10-08
36Mistral Large 4 Mistral AI1541LMArena2026-10-08
37Claude Sonnet 5 Anthropic1541highLMArena2026-10-08
38Gemini 3.6 Flash Google1538highLMArena2026-10-08
39Muse Spark 1.2 Meta1533muse-spark-1.2 (xHigh)LMArena2026-10-08
40Claude Sonnet 4.6 Anthropic1522LMArena2026-10-08
41GPT-5.6 Terra OpenAI1522LMArena2026-10-08
42GPT-5.6 Luna OpenAI1519LMArena2026-10-08
43Qwen3.7 Max Alibaba (Qwen)1515LMArena2026-10-08
44GPT-5.5 OpenAI1513LMArena2026-10-08
45Kimi K2.6 Moonshot AI1509LMArena2026-10-08
46Hy3 Tencent1508LMArena2026-10-08
47GLM-5.1 Z.ai (Zhipu)1508LMArena2026-10-08
48Gemini 3.5 Flash Google1499highLMArena2026-10-08
49Claude Opus 4.5 Anthropic1494LMArena2026-10-08
50Qwen3.6 Max Preview Alibaba (Qwen)1482LMArena2026-10-08
51MiniMax-M3 MiniMax1482LMArena2026-10-08
52MiMo-V2.5-Pro Xiaomi1479LMArena2026-10-08
53Kimi K2.7 Code Moonshot AI1473LMArena2026-10-08
54GPT-5.4 OpenAI1465LMArena2026-10-08
55Qwen3.6 Plus Alibaba (Qwen)1461LMArena2026-10-08
56Gemini 3.1 Pro Preview Google1447LMArena2026-10-08
57Gemini 3.5 Flash Lite Google1440LMArena2026-10-08
58Gemini 3 Pro Google1440LMArena2026-10-08
59Gemini 3 Flash Preview Google1439LMArena2026-10-08
60MiMo-V2.5 Xiaomi1438LMArena2026-10-08
61Kimi K2.5 Moonshot AI1437thinkingLMArena2026-10-08
62GLM-4.7 Z.ai (Zhipu)1435LMArena2026-10-08
63GLM-5 Z.ai (Zhipu)1434LMArena2026-10-08
64MiMo-V2-Pro Xiaomi1433LMArena2026-10-08
65GPT-5 OpenAI1418mediumLMArena2026-10-08
66GPT-5.2 OpenAI1416LMArena2026-10-08
67Inkling Thinking Machines Lab1413LMArena2026-10-08
68Inkling-Small Thinking Machines Lab1409Inkling SmallLMArena2026-10-08
69GPT-5.3 Codex OpenAI1409LMArena2026-10-08
70Kimi K2.5 Instant Moonshot AI1404LMArena2026-10-08
71GLM-5V-Turbo Z.ai (Zhipu)1401LMArena2026-10-08
72Qwen3.5 397B-A17B Alibaba (Qwen)1400LMArena2026-10-08
73MiniMax-M2.7 MiniMax1398LMArena2026-10-08
74GPT-5.4 mini OpenAI1397highLMArena2026-10-08
75GPT-5.1 OpenAI1395mediumLMArena2026-10-08
76Claude Sonnet 4.5 Anthropic1393LMArena2026-10-08
77Claude Opus 4.1 Anthropic1390LMArena2026-10-08
78MiniMax-M2.5 MiniMax1387LMArena2026-10-08
79MiniMax-M2.1 MiniMax1384LMArena2026-10-08
80Grok 4.20 (Non-Reasoning) xAI1375LMArena2026-10-08
81Solar Pro4 Upstage1371LMArena2026-10-08
82Gemma 4 31B IT Google1366LMArena2026-10-08
83DeepSeek-V3.2-Exp DeepSeek1362thinkingLMArena2026-10-08
84Qwen3.5 122B-A10B Alibaba (Qwen)1360LMArena2026-10-08
85Gemma 4 26B A4B IT Google1359LMArena2026-10-08
86Qwen3.5 27B Alibaba (Qwen)1358LMArena2026-10-08
87Grok 4.3 xAI1357LMArena2026-10-08
88Muse Glimmer Meta1355LMArena2026-10-08
89Laguna M.1 Poolside1349LMArena2026-10-08
90GLM-4.6 Z.ai (Zhipu)1340LMArena2026-10-08
91GPT-5.2 Codex OpenAI1339LMArena2026-10-08
92GPT-5.1-Codex OpenAI1337LMArena2026-10-08
93MiMo-V2-Flash Xiaomi1330LMArena2026-10-08
94Claude Haiku 4.5 Anthropic1330LMArena2026-10-08
95Kimi K2 Thinking Turbo Moonshot AI1322LMArena2026-10-08
96Laguna XS.2 Poolside1302LMArena2026-10-08
97MiniMax-M2 MiniMax1297LMArena2026-10-08
98Qwen3-Coder 480B-A35B Instruct Alibaba (Qwen)1275LMArena2026-10-08
99Mistral Medium 3.5 Mistral AI1264LMArena2026-10-08
100Gemini 3.1 Flash Lite Google1256LMArena2026-10-08
101Qwen3.5 35B-A3B Alibaba (Qwen)1254LMArena2026-10-08
102GPT-5.1-Codex-mini OpenAI1244LMArena2026-10-08
103Qwen3.5-Flash Alibaba (Qwen)1244LMArena2026-10-08
104Grok 4.1 Fast xAI1242LMArena2026-10-08
105Trinity Large Thinking Arcee AI1238thinkingLMArena2026-10-08
106Mistral Large 3 Mistral AI1230LMArena2026-10-08
107Gemini 2.5 Pro Google1227LMArena2026-10-08
108Grok 4.1 xAI1214thinkingLMArena2026-10-08
109Devstral 2 Mistral AI1197LMArena2026-10-08
110Granite 4.1 8b IBM1192LMArena2026-10-08
111Mercury 2 Inception1171LMArena2026-10-08
112Grok 4 Fast xAI1159LMArena2026-10-08
113Devstral Medium Mistral AI1076LMArena2026-10-08

Compare the leaders

Other coding benchmarks

Frequently asked questions

What does LMArena WebDev measure?

Blind votes on web apps built by two anonymous models from the same prompt.

Which model has the highest LMArena WebDev score?

As of October 2026, Claude Opus 5.5 has the highest published LMArena WebDev score on Noometry at 1813, out of 113 models with results.

What is the best open-weight model on LMArena WebDev?

Kimi K3 has the highest LMArena WebDev rating among open-weight models at 1654, ranking 11 of 113 overall.