LMArena WebDev leaderboard

People ask two anonymous models to build the same web app, try both and vote for the better one. Claude Opus 5.5 leads with a rating of 1807.

Models: 124
Leader: Claude Opus 5.5
Source: LMArena
As of: Oct 22, 2026

LMArena WebDev, rating against blended price per million tokens

Open weightsProprietaryBest for the price

Full leaderboard

Rank	Model	Lab	Rating	95% interval	Votes	Price in / out
1	Claude Opus 5.5	Anthropic	1807	1794–1820	3.1K	$4 / $20
2	GPT-6 Astra	OpenAI	1774	1764–1784	6.6K	$10 / $50
3	Claude Sonnet 5.5	Anthropic	1769	1757–1781	3.8K	$2 / $10
4	GPT-6.1 Sol	OpenAI	1749	1737–1762	3.5K	$2 / $10
5	Claude Fable 5.1	Anthropic	1743	1734–1751	8.1K	$10 / $50
6	Muse Wonder Full	Meta	1726	1712–1740	2.3K	—
8	Kimi K3.1 Pro	Moonshot AI	1692	1678–1705	2.5K	$2 / $10
9	Claude Opus 5	Anthropic	1691	1685–1697	19K	$5 / $25
10	GPT-6 Sol	OpenAI	1681	1671–1691	5K	$2 / $10
11	Gemini 4 Argon	Google	1674	1662–1687	2.7K	$2 / $10
12	Qwen3.8-Max	Alibaba	1673	1666–1680	15.6K	$2 / $6
14	DeepSeek-V4.1-Flash-20260910	DeepSeek	1665	1652–1678	2.5K	$0.15 / $0.60
16	Muse Spark 1.3	Meta	1657	1650–1665	9.9K	$1.25 / $4.25
17	Kimi K3	Moonshot AI	1655	1649–1661	20.3K	$0.24 / $11
18	Muse Wonder	Meta	1651	1638–1664	2.7K	$4 / $20
19	Grok 4.7	xAI	1638	1629–1647	5.7K	$2 / $6
20	MiMo-V2.6-Flash	Xiaomi	1635	1626–1644	5.7K	$0.14 / $0.28
21	Hy4 preview	Tencent	1631	1622–1641	4.8K	$0.75 / $2.25
22	Qwen3.8-Flash-Next	Alibaba	1629	1621–1637	8.9K	—
23	MiMo-V2.6-Pro	Xiaomi	1625	1616–1635	5.7K	$0.43 / $0.87
24	Claude Fable 5	Anthropic	1624	1618–1630	16.3K	$10 / $50
25	GLM-5.3	Z.ai	1623	1615–1630	10.3K	$0.079 / $1.40
28	Grok 4.6	xAI	1617	1610–1624	11K	$2 / $6
29	GPT-5.6 Sol	OpenAI	1615	1609–1621	18.2K	$4 / $20
30	GLM-5.3-Flash	Z.ai	1608	1601–1614	19.7K	$0.15 / $0.50
31	GLM-5.2	Z.ai	1604	1598–1610	17.1K	$0.034 / $7
32	Qwen3.8-27B	Alibaba	1591	1585–1598	17.2K	$0.20 / $2.50
33	Gemini 3.7 Flash	Google	1590	1584–1597	13.3K	$0.75 / $3.75
34	MiniMax-M3.1-Flash	MiniMax	1589	1576–1602	2.2K	$0.15 / $0.60
35	Claude Haiku 5.5	Anthropic	1586	1575–1596	3.9K	$0.10 / $0.50
36	Gemini 3.8 Flash	Google	1585	1578–1592	11.4K	$0.82 / $4.13
37	DeepSeek-V4-Pro	DeepSeek	1582	1573–1592	4.7K	$0.66 / $1.98
38	DeepSeek-V4-Flash	DeepSeek	1582	1573–1591	4.9K	$0.042 / $0.18
39	GPT-6 Luna	OpenAI	1579	1573–1585	24.4K	$0.10 / $0.50
40	Step 5 Preview	StepFun	1568	1559–1577	5.2K	$1 / $2.70
41	Claude Opus 4.7	Anthropic	1558	1552–1564	17.9K	$5 / $25
42	Claude Opus 4.8	Anthropic	1556	1550–1562	18.5K	$5 / $25
44	Grok 4.5	xAI	1553	1546–1560	11.1K	$2 / $6
45	Claude Opus 4.6	Anthropic	1546	1541–1552	19.4K	$5 / $25
46	Mistral Large 4	Mistral AI	1545	1533–1556	3.3K	$1.36 / $4.18
47	Muse Spark 1.1	Meta	1543	1535–1550	8K	$1.25 / $4.25
48	Claude Sonnet 5	Anthropic	1541	1535–1546	16.2K	$2 / $10
49	Gemini 3.6 Flash	Google	1538	1531–1546	8.8K	$0.75 / $3.75
52	Muse Spark 1.2	Meta	1533	1520–1547	2.2K	$1.25 / $4.25
53	Muse Spark Open	Meta	1526	1510–1543	1.5K	$1.25 / $4.25
54	Claude Sonnet 4.6	Anthropic	1523	1518–1528	22.9K	$3 / $15
55	GPT-5.6 Terra	OpenAI	1521	1514–1527	14.5K	$2 / $12
56	Seed2.1 Pro Preview	ByteDance	1520	1514–1526	15.5K	—
57	GPT-5.6 Luna	OpenAI	1519	1513–1525	12.6K	$0.20 / $1.20
58	Qwen3.7-Max-Preview	Alibaba	1515	1508–1523	8.9K	$1.48 / $4.42
59	GPT-5.5	OpenAI	1513	1507–1519	15.6K	$5 / $30
60	Kimi K2.6	Moonshot AI	1509	1502–1517	10.2K	$0.65 / $3.41
61	GLM-5.1	Z.ai	1508	1501–1515	10.7K	$1.40 / $4.40
62	Hy3	Tencent	1506	1498–1514	6.4K	$0.083 / $0.33
63	Gemini 3.5 Flash	Google	1499	1492–1506	9.4K	$1.50 / $9
64	Claude Opus 4.5	Anthropic	1494	1486–1502	11K	$5 / $25
67	MiniMax-M3	MiniMax	1482	1477–1488	20.3K	$0.30 / $1.20
68	Qwen3.6-Max-Preview	Alibaba	1482	1470–1495	2.7K	—
69	MiMo-V2.5-Pro	Xiaomi	1481	1475–1486	22.8K	$0.30 / $0.61
70	Spark-X2.6	Synlan	1480	1460–1500	1.1K	—
71	Kimi K2.7 Code	Moonshot AI	1474	1464–1483	5K	$0.67 / $3.35
74	GPT-5.4	OpenAI	1464	1445–1483	1.4K	$2.50 / $15
75	Qwen3.6-Plus	Alibaba	1462	1456–1467	18.6K	$0.33 / $1.95
78	Gemini 3.1 Pro Preview	Google	1447	1442–1452	24.2K	$2 / $12
80	Gemini 3 Pro	Google	1440	1432–1449	14.1K	—
81	Gemini 3 Flash	Google	1440	1432–1449	10.9K	$0.50 / $3
82	MiMo-V2.5	Xiaomi	1438	1432–1444	14.9K	$0.12 / $0.24
83	Kimi K2.5	Moonshot AI	1437	1431–1442	20.1K	$0.50 / $2.50
84	Beam 1.0 501B A23B	Reflection AI	1436	1424–1449	2.9K	$0.25 / $1
85	GLM-4.7	Z.ai	1435	1423–1448	4K	$0.54 / $1.98
86	GLM-5	Z.ai	1435	1427–1444	7.5K	$1 / $3.20
87	Gemini 3.5 Flash-Lite	Google	1434	1393–1475	237	$0.30 / $2.50
88	MiMo-V2-Pro	Xiaomi	1434	1426–1442	7.3K	—
90	GPT-5	OpenAI	1418	1402–1433	3.1K	$1.25 / $10
91	GPT-5.2	OpenAI	1417	1394–1439	1.1K	$1.75 / $14
92	Inkling	Thinky	1415	1409–1421	16.3K	$1 / $4.05
93	Inkling-Small	Thinky	1409	1400–1418	5.3K	$0.45 / $1.20
94	GPT-5.3-Codex	OpenAI	1407	1393–1420	2.6K	$1.75 / $14
96	GLM-5V-Turbo	Z.ai	1402	1388–1415	2.4K	$1.20 / $4
98	Qwen3.5-397B-A17B	Alibaba	1400	1395–1405	21.2K	$0.50 / $3.60
99	MiniMax-M2.7	MiniMax	1398	1392–1404	16K	$0.30 / $1.20
100	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B	NVIDIA	1398	1383–1413	2.3K	—
101	GPT-5.4 mini	OpenAI	1398	1391–1404	12K	$0.75 / $4.50
102	GPT-5.1	OpenAI	1396	1384–1407	4.9K	$1.25 / $10
103	Claude Sonnet 4.5	Anthropic	1394	1386–1402	13.3K	$3 / $15
104	Claude Opus 4.1	Anthropic	1391	1380–1401	6.9K	$15 / $75
105	MiniMax-M2.5	MiniMax	1386	1378–1395	7.6K	$0.30 / $1.20
108	MiniMax-M2.1 Preview	MiniMax	1385	1375–1394	7.6K	$0.30 / $1.20
109	Grok 4.20 Beta	xAI	1376	1369–1382	15.5K	—
111	Solar Pro 4	Upstage	1370	1360–1381	4.7K	$0.15 / $0.60
112	Gemma 4 31B	Google	1368	1362–1375	15K	$0.20 / $0.40
113	DeepSeek-V3.2-Exp	DeepSeek	1363	1353–1372	6.9K	$0.28 / $0.42
114	Qwen3.5-122B-A10B	Alibaba	1361	1353–1368	8.3K	$0.40 / $3.20
115	Gemma 4 26B A4B	Google	1360	1343–1377	1.5K	$0.068 / $0.23
116	Qwen3.5-27B	Alibaba	1359	1351–1367	7.8K	$0.27 / $2.16
117	Grok 4.3	xAI	1358	1351–1364	15K	$1.25 / $2.50
119	Muse Glimmer	Meta	1355	1339–1370	1.6K	—
120	Laguna M.1	Poolside	1349	1340–1358	5.4K	—
122	GLM-4.6	Z.ai	1341	1331–1352	6.8K	$0.55 / $2.20
123	GPT-5.2-Codex	OpenAI	1339	1330–1348	6.7K	$1.75 / $14
124	GPT-5.1-Codex	OpenAI	1337	1326–1349	5K	$1.25 / $10
125	MiMo-V2-Flash	Xiaomi	1331	1321–1340	5.7K	—
126	Claude Haiku 4.5	Anthropic	1331	1326–1335	29.1K	$1 / $5
128	Kimi K2 Thinking Turbo	Moonshot AI	1323	1315–1330	13.1K	—
129	Laguna XS.2	Poolside	1303	1292–1313	4.2K	—
130	MiniMax-M2	MiniMax	1297	1286–1308	6.7K	$0.26 / $1.02
132	Qwen3-Coder-480B-A35B-Instruct	Alibaba	1275	1267–1283	12.7K	—
134	Mistral Medium 3.5	Mistral AI	1264	1249–1279	2.3K	$1.50 / $7.50
135	Gemini 3.1 Flash-Lite Preview	Google	1256	1250–1263	14.4K	$0.25 / $1.50
136	KAT-Coder-Pro V1	—	1256	1237–1276	1.5K	—
137	Qwen3.5-35B-A3B	Alibaba	1254	1237–1272	1.6K	$0.14 / $1
138	GPT-5.1-Codex-Mini	OpenAI	1244	1222–1266	1.2K	$0.25 / $2
139	Qwen3.5-Flash	Alibaba	1244	1224–1263	1.3K	$0.065 / $0.26
140	Grok 4.1 Fast	xAI	1242	1231–1253	5.5K	—
141	Trinity Large Thinking	Arcee	1238	1218–1258	1.4K	$0.25 / $0.80
142	Mistral Large 3	Mistral AI	1232	1206–1257	840	$0.50 / $1.50
143	Gemini 2.5 Pro	Google	1227	1211–1242	2.7K	$1.25 / $10
144	Grok 4.1	xAI	1215	1190–1240	961	—
145	Devstral 2	Mistral AI	1197	1177–1218	1.2K	$0.40 / $2
146	Granite 4.1 8B	IBM	1192	1174–1211	1.8K	—
147	Mercury 2	Inception	1171	1146–1195	954	$0.25 / $0.75
148	Grok Code Fast 1	xAI	1167	1138–1195	789	—
149	Grok 4 Fast	xAI	1160	1133–1187	743	—
150	Devstral Medium	Mistral AI	1072	1041–1102	842	—

LMArena ranks overlap where confidence intervals do, so several models can share a rank. Where a model is rated at several effort levels, its best is shown.

Full leaderboard

Related leaderboards