Code Arena | WebDev🎨Reference-Based Design

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

98,156 votes

80 models

Rank by

	Rank Spread
1	13	claude-opus-4-7-thinking Anthropic · Proprietary	1590+15/-15	1,859	$5 / $25	1M
2	14	claude-opus-4-7 Anthropic · Proprietary	1583+16/-16	1,735	$5 / $25	1M
3	16	claude-opus-4-6-thinking Anthropic · Proprietary	1564+14/-14	2,324	$5 / $25	1M
4	310	claude-opus-4-6 Anthropic · Proprietary	1546+13/-13	2,657	$5 / $25	1M
5	212	qwen3.7-max-20260517 Alibaba · Proprietary	1543+26/-26	532	$1.25 / $3.75	1M
6	312	glm-5.1 Z.ai · MIT	1540+20/-20	1,039	$1.40 / $4.40	202.8K
7	412	claude-sonnet-4-6 Anthropic · Proprietary	1536+11/-11	3,317	$3 / $15	1M
8	414	gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary	1525+17/-17	1,373	N/A	N/A
9	515	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1517+12/-12	3,626	$5 / $25	200K
10	416	muse-spark Meta · Proprietary	1516+29/-29	480	N/A	N/A
11	515	kimi-k2.6 Moonshot · Modified MIT	1513+18/-18	1,212	$0.95 / $4	262.1K
12	416	gemini-3.5-flash Google · Proprietary	1513+24/-24	727	$1.50 / $9	1M
13	820	deepseek-v4-pro-thinking DeepSeek · MIT	1492+17/-17	1,273	$0.43 / $0.87	1M
14	821	qwen3.6-max-preview Alibaba · Proprietary	1491+22/-22	828	$1.04 / $6.24	262.1K
15	920	gpt-5.5-high (codex-harness) OpenAI · Proprietary	1490+16/-16	1,474	N/A	N/A
16	1323	claude-opus-4-5-20251101 Anthropic · Proprietary	1474+10/-10	4,205	$5 / $25	200K
17	1327	mimo-v2.5-pro Xiaomi · MIT	1470+16/-16	1,539	$0.43 / $0.87	1M
18	1330	qwen3.6-plus Alibaba · Proprietary	1464+14/-14	1,948	$0.33 / $1.95	1M
19	1131	gpt-5.4-medium (codex-harness) OpenAI · Proprietary	1462+29/-29	427	$2.50 / $15	1.1M
20	1530	gemini-3.1-pro-preview Google · Proprietary	1461+11/-11	3,174	$2 / $12	1M
21	1334	gpt-5.4-high (codex-harness) OpenAI · Proprietary	1455+31/-31	432	$2.50 / $15	1.1M
22	1731	gemini-3-pro Google · Proprietary	1452+11/-11	5,048	$2 / $12	1M
23	1631	gpt-5.5 (codex-harness) OpenAI · Proprietary	1450+17/-17	1,345	N/A	N/A
24	1633	glm-4.7 Z.ai · MIT	1448+18/-18	1,313	$0.40 / $1.75	202.8K
25	1733	glm-5 Z.ai · MIT	1446+15/-15	1,695	$1 / $3.20	202.8K
26	1734	mimo-v2-pro Xiaomi · Proprietary	1441+14/-14	2,139	$1 / $3	1M
27	1834	kimi-k2.5-thinking Moonshot · Modified MIT	1440+11/-11	3,075	$0.60 / $3	N/A
28	1834	gemini-3-flash Google · Proprietary	1439+12/-12	3,700	$0.50 / $3	1M
29	1834	mimo-v2.5 Xiaomi · MIT	1434+18/-18	1,185	$0.14 / $0.28	1M
30	2038	kimi-k2.5-instant Moonshot · Modified MIT	1427+21/-21	896	$0.40 / $1.90	262.1K
31	1746	gpt-5.2 OpenAI · Proprietary	1425+31/-31	435	$1.75 / $14	400K
32	2542	gpt-5.4-mini-high OpenAI · Proprietary	1415+15/-15	1,682	$0.75 / $4.50	400K
33	2346	gpt-5-medium OpenAI · Proprietary	1414+19/-19	1,258	$1.25 / $10	400K
34	2347	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1410+22/-22	755	$1.75 / $14	400K
35	3047	gpt-5.1-medium OpenAI · Proprietary	1399+15/-15	1,796	$1.25 / $10	400K
36	3047	claude-opus-4-1-20250805 Anthropic · Proprietary	1396+14/-14	2,634	$15 / $75	200K
37	3047	grok-4.20-beta-0309-reasoning xAI · Proprietary	1396+13/-13	2,238	$2 / $6	2M
38	3147	gemini-3-flash (thinking-minimal) Google · Proprietary	1392+9/-9	4,749	$0.50 / $3	1M
39	3150	minimax-m2.7 MiniMax · Modified MIT	1392+14/-14	1,946	$0.28 / $1.20	204.8K
40	3150	qwen3.5-397b-a17b Alibaba · Apache 2.0	1389+11/-11	2,990	$0.39 / $2.34	262.1K
41	3250	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1388+10/-10	4,617	$3 / $15	200K
42	3250	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1386+10/-10	5,427	$3 / $15	200K
43	3152	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1385+19/-19	1,056	$1.75 / $14	400K
44	3251	minimax-m2.1-preview MiniMax · MIT	1382+13/-13	2,345	$0.29 / $0.95	204.8K
45	3055	hunyuan-hy3-preview Tencent · tencent-hunyuan-community	1377+30/-30	442	N/A	N/A
46	3253	grok-4.3 xAI · Proprietary	1377+18/-18	1,187	$1.25 / $2.50	1M
47	3953	minimax-m2.5 MiniMax · Modified MIT	1369+13/-13	2,020	$0.15 / $1.15	204.8K
48	3953	qwen3.5-122b-a10b Alibaba · Apache 2.0	1368+12/-12	2,457	$0.26 / $2.08	262.1K
49	3956	gemma-4-31b Google · Apache 2.0	1363+20/-20	969	$0.14 / $0.40	262.1K
50	3458	gemma-4-26b-a4b Google · Apache 2.0	1360+29/-29	439	N/A	N/A
51	4355	deepseek-v3.2-thinking DeepSeek · MIT	1357+13/-13	2,243	$0.25 / $0.38	131.1K
52	4456	qwen3.5-27b Alibaba · Apache 2.0	1354+13/-13	2,292	$0.20 / $1.56	262.1K
53	4558	glm-4.6 Z.ai · MIT	1347+14/-14	2,598	$0.43 / $1.74	202.8K
54	4859	gpt-5.2-codex OpenAI · Proprietary	1341+14/-14	2,150	$1.75 / $14	400K
55	4859	gpt-5.1 OpenAI · Proprietary	1341+11/-11	3,853	$1.25 / $10	400K
56	5061	gpt-5.1-codex OpenAI · Proprietary	1329+15/-15	1,923	$1.25 / $10	400K
57	5261	mimo-v2-flash (non-thinking) Xiaomi · MIT	1325+15/-15	1,758	$0.10 / $0.30	262.1K
58	5261	deepseek-v3.2 DeepSeek · MIT	1323+12/-12	2,982	$0.25 / $0.38	131.1K
59	5461	kimi-k2-thinking-turbo Moonshot · Modified MIT	1320+10/-10	4,549	$1.15 / $8	262.1K
60	5662	claude-haiku-4-5-20251001 Anthropic · Proprietary	1313+9/-9	6,163	$1 / $5	200K
61	6065	minimax-m2 MiniMax · Apache 2.0	1294+14/-14	2,690	$0.26 / $1	204.8K
62	5669	mimo-v2-flash (thinking) Xiaomi · MIT	1289+25/-25	574	$0.10 / $0.30	262.1K
63	6169	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1273+10/-10	4,458	$0.40 / $1.60	262.1K
64	6170	deepseek-v3.2-exp DeepSeek · MIT	1272+16/-16	1,640	$0.27 / $0.41	163.8K
65	6176	qwen3.5-35b-a3b Alibaba · Apache 2.0	1256+27/-27	533	$0.14 / $1	262.1K
66	6274	gemini-3.1-flash-lite-preview Google · Proprietary	1254+13/-13	2,872	$0.25 / $1.50	1M
67	6276	KAT-Coder-Pro-V1 KwaiKAT · Proprietary	1245+24/-24	640	$0.21 / $0.83	256K
68	6276	qwen3.5-flash Alibaba · Proprietary	1242+31/-31	439	N/A	N/A
69	6277	trinity-large-thinking Arcee AI · Apache 2.0	1231+37/-37	357	$0.22 / $0.85	262.1K
70	6576	grok-4-1-fast-reasoning xAI · Proprietary	1229+15/-15	1,990	$0.20 / $0.50	2M
71	6477	gpt-5.1-codex-mini OpenAI · Proprietary	1229+29/-29	494	$0.25 / $2	400K
72	6577	granite-4.1-8b IBM · Apache 2.0	1224+29/-29	574	$0.05 / $0.10	131.1K
73	6578	mistral-large-3 Mistral · Apache 2.0	1209+36/-36	304	$0.50 / $1.50	N/A
74	6578	grok-4.1-thinking xAI · Proprietary	1207+35/-35	372	N/A	N/A
75	6679	devstral-2 Mistral · Modified MIT	1198+31/-31	415	N/A	N/A
76	6679	mercury-2 Inception AI · Proprietary	1188+41/-41	278	$0.25 / $0.75	128K
77	7079	gemini-2.5-pro Google · Proprietary	1186+20/-20	1,111	$1.25 / $10	1M
78	7380	grok-4-fast-reasoning xAI · Proprietary	1136+41/-41	287	$0.20 / $0.50	2M
79	7580	grok-code-fast-1 xAI · Proprietary	1133+38/-38	322	$0.20 / $1.50	N/A
80	7880	devstral-medium-2507 Mistral · Proprietary	1069+41/-41	312	$0.40 / $2	128K

Code Arena | WebDev🎨Reference-Based Design

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🎨Reference-Based Design

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)