Code Arena | WebDev🧪Simulations

View overall rankings across AI models on front-end web development tasks, including agentic coding workflows that require multi-step reasoning and tool use.

May 24, 2026

48,264 votes

79 models

Rank by

	Rank Spread
1	16	claude-opus-4-7 Anthropic · Proprietary	1594+26/-26	635	$5 / $25	1M
2	18	claude-opus-4-7-thinking Anthropic · Proprietary	1592+27/-27	660	$5 / $25	1M
3	19	glm-5.1 Z.ai · MIT	1585+33/-33	390	$1.40 / $4.40	202.8K
4	114	qwen3.7-max-20260517 Alibaba · Proprietary	1577+50/-50	171	$1.25 / $3.75	1M
5	113	claude-opus-4-6-thinking Anthropic · Proprietary	1559+21/-21	1,022	$5 / $25	1M
6	115	gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary	1549+29/-29	522	N/A	N/A
7	214	claude-opus-4-6 Anthropic · Proprietary	1547+19/-19	1,139	$5 / $25	1M
8	217	qwen3.6-max-preview Alibaba · Proprietary	1530+35/-35	291	$1.04 / $6.24	262.1K
9	417	claude-sonnet-4-6 Anthropic · Proprietary	1521+18/-18	1,327	$3 / $15	1M
10	418	kimi-k2.6 Moonshot · Modified MIT	1520+28/-28	491	$0.95 / $4	262.1K
11	521	gpt-5.5-high (codex-harness) OpenAI · Proprietary	1511+27/-27	551	N/A	N/A
12	326	gpt-5.4-high (codex-harness) OpenAI · Proprietary	1510+51/-51	166	$2.50 / $15	1.1M
13	422	gemini-3.5-flash Google · Proprietary	1508+39/-39	281	$1.50 / $9	1M
14	428	muse-spark Meta · Proprietary	1495+48/-48	173	N/A	N/A
15	822	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1494+15/-15	2,062	$5 / $25	200K
16	826	mimo-v2.5-pro Xiaomi · MIT	1480+26/-26	597	$0.43 / $0.87	1M
17	1126	gemini-3.1-pro-preview Google · Proprietary	1471+18/-18	1,189	$2 / $12	1M
18	1028	qwen3.6-plus Alibaba · Proprietary	1470+24/-24	699	$0.33 / $1.95	1M
19	735	gpt-5.4-medium (codex-harness) OpenAI · Proprietary	1470+52/-52	141	$2.50 / $15	1.1M
20	1226	claude-opus-4-5-20251101 Anthropic · Proprietary	1465+14/-14	2,359	$5 / $25	200K
21	1132	deepseek-v4-pro-thinking DeepSeek · MIT	1460+28/-28	503	$0.43 / $0.87	1M
22	1133	gpt-5.5 (codex-harness) OpenAI · Proprietary	1458+27/-27	529	N/A	N/A
23	1434	mimo-v2-pro Xiaomi · Proprietary	1446+21/-21	845	$1 / $3	1M
24	1432	gemini-3-pro Google · Proprietary	1446+14/-14	3,154	$2 / $12	1M
25	1435	glm-5 Z.ai · MIT	1441+21/-21	916	$1 / $3.20	202.8K
26	1444	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1430+34/-34	359	$1.75 / $14	400K
27	2037	kimi-k2.5-thinking Moonshot · Modified MIT	1429+17/-17	1,314	$0.60 / $3	N/A
28	2038	minimax-m2.5 MiniMax · Modified MIT	1424+18/-18	1,154	$0.15 / $1.15	204.8K
29	1842	gpt-5.4-mini-high OpenAI · Proprietary	1424+25/-25	664	$0.75 / $4.50	400K
30	1844	mimo-v2.5 Xiaomi · MIT	1420+28/-28	480	$0.14 / $0.28	1M
31	2241	gemini-3-flash Google · Proprietary	1417+15/-15	2,099	$0.50 / $3	1M
32	2044	minimax-m2.7 MiniMax · Modified MIT	1412+21/-21	860	$0.28 / $1.20	204.8K
33	2346	glm-4.7 Z.ai · MIT	1408+22/-22	867	$0.40 / $1.75	202.8K
34	2046	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1404+31/-31	408	$1.75 / $14	400K
35	2446	gemma-4-31b Google · Apache 2.0	1392+30/-30	450	$0.14 / $0.40	262.1K
36	2746	qwen3.5-397b-a17b Alibaba · Apache 2.0	1391+18/-18	1,121	$0.39 / $2.34	262.1K
37	2846	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1390+13/-13	2,710	$3 / $15	200K
38	2846	gemini-3-flash (thinking-minimal) Google · Proprietary	1389+13/-13	2,264	$0.50 / $3	1M
39	3046	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1386+13/-13	3,144	$3 / $15	200K
40	2648	kimi-k2.5-instant Moonshot · Modified MIT	1385+27/-27	521	$0.40 / $1.90	262.1K
41	3046	minimax-m2.1-preview MiniMax · MIT	1382+16/-16	1,569	$0.29 / $0.95	204.8K
42	2947	grok-4.20-beta-0309-reasoning xAI · Proprietary	1380+21/-21	881	$2 / $6	2M
43	2853	grok-4.3 xAI · Proprietary	1375+30/-30	422	$1.25 / $2.50	1M
44	3348	claude-opus-4-1-20250805 Anthropic · Proprietary	1374+16/-16	1,742	$15 / $75	200K
45	2659	hunyuan-hy3-preview Tencent · tencent-hunyuan-community	1364+50/-50	168	N/A	N/A
46	3358	gpt-5.2 OpenAI · Proprietary	1353+36/-36	304	$1.75 / $14	400K
47	4155	deepseek-v3.2-thinking DeepSeek · MIT	1343+18/-18	1,235	$0.25 / $0.38	131.1K
48	4456	glm-4.6 Z.ai · MIT	1339+16/-16	1,766	$0.43 / $1.74	202.8K
49	4257	qwen3.5-122b-a10b Alibaba · Apache 2.0	1338+20/-20	1,003	$0.26 / $2.08	262.1K
50	4458	qwen3.5-27b Alibaba · Apache 2.0	1337+20/-20	969	$0.20 / $1.56	262.1K
51	4458	gpt-5.1-medium OpenAI · Proprietary	1334+18/-18	1,246	$1.25 / $10	400K
52	4460	gpt-5.2-codex OpenAI · Proprietary	1328+19/-19	1,078	$1.75 / $14	400K
53	4560	mimo-v2-flash (non-thinking) Xiaomi · MIT	1325+19/-19	1,105	$0.10 / $0.30	262.1K
54	4662	kimi-k2-thinking-turbo Moonshot · Modified MIT	1311+13/-13	2,623	$1.15 / $8	262.1K
55	4563	gpt-5-medium OpenAI · Proprietary	1310+23/-23	778	$1.25 / $10	400K
56	4762	gpt-5.1 OpenAI · Proprietary	1306+14/-14	2,252	$1.25 / $10	400K
57	4469	gemma-4-26b-a4b Google · Apache 2.0	1298+55/-55	148	N/A	N/A
58	5263	deepseek-v3.2 DeepSeek · MIT	1298+16/-16	1,578	$0.25 / $0.38	131.1K
59	5165	gpt-5.1-codex OpenAI · Proprietary	1297+19/-19	1,233	$1.25 / $10	400K
60	5463	claude-haiku-4-5-20251001 Anthropic · Proprietary	1293+12/-12	3,321	$1 / $5	200K
61	5466	deepseek-v3.2-exp DeepSeek · MIT	1284+20/-20	1,059	$0.27 / $0.41	163.8K
62	4868	mimo-v2-flash (thinking) Xiaomi · MIT	1283+36/-36	296	$0.10 / $0.30	262.1K
63	5968	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1266+13/-13	2,646	$0.40 / $1.60	262.1K
64	5968	minimax-m2 MiniMax · Apache 2.0	1263+17/-17	1,690	$0.26 / $1	204.8K
65	6172	gemini-3.1-flash-lite-preview Google · Proprietary	1243+21/-21	1,099	$0.25 / $1.50	1M
66	5674	trinity-large-thinking Arcee AI · Apache 2.0	1238+51/-51	178	$0.22 / $0.85	262.1K
67	6074	qwen3.5-35b-a3b Alibaba · Apache 2.0	1228+42/-42	232	$0.14 / $1	262.1K
68	6175	mistral-large-3 Mistral · Apache 2.0	1220+44/-44	207	$0.50 / $1.50	N/A
69	6475	KAT-Coder-Pro-V1 KwaiKAT · Proprietary	1214+32/-32	408	$0.21 / $0.83	256K
70	6575	grok-4-1-fast-reasoning xAI · Proprietary	1203+20/-20	1,121	$0.20 / $0.50	2M
71	6577	gpt-5.1-codex-mini OpenAI · Proprietary	1188+36/-36	321	$0.25 / $2	400K
72	6677	gemini-2.5-pro Google · Proprietary	1182+25/-25	721	$1.25 / $10	1M
73	6579	qwen3.5-flash Alibaba · Proprietary	1173+55/-55	150	N/A	N/A
74	6679	granite-4.1-8b IBM · Apache 2.0	1170+46/-46	247	$0.05 / $0.10	131.1K
75	6879	devstral-2 Mistral · Modified MIT	1137+47/-47	205	N/A	N/A
76	7179	grok-code-fast-1 xAI · Proprietary	1127+48/-48	209	$0.20 / $1.50	N/A
77	7179	grok-4-fast-reasoning xAI · Proprietary	1115+52/-52	181	$0.20 / $0.50	2M
78	7379	grok-4.1-thinking xAI · Proprietary	1093+44/-44	236	N/A	N/A
79	7379	devstral-medium-2507 Mistral · Proprietary	1085+46/-46	239	$0.40 / $2	128K

Code Arena | WebDev🧪Simulations

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Fraction of Model A Wins for All Non-tied A vs. B Battles

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)

Domain

Code Arena | WebDev🧪Simulations

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Fraction of Model A Wins for All Non-tied A vs. B Battles

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)