Code Arena | WebDev🏆Overall

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

Jul 1, 2026

422,204 votes

92 models

Rank by

	Rank Spread
1	11	claude-fable-5 Anthropic · Proprietary	1653+15/-15	2,100	$10 / $50	1M
2	22	glm-5.2 (max) Z.ai · MIT	1584+12/-12	3,015	$1.40 / $4.40	1M
3	37	claude-opus-4-8-thinking Anthropic · Proprietary	1561+10/-10	4,071	$5 / $25	1M
4	37	claude-opus-4-7-thinking Anthropic · Proprietary	1559+8/-8	8,857	$5 / $25	1M
5	37	claude-opus-4-7 Anthropic · Proprietary	1557+8/-8	8,357	$5 / $25	1M
6	311	claude-sonnet-5-thinking Anthropic · Proprietary	1551+18/-18	1,250	$2 / $10	1M
7	611	claude-opus-4-6-thinking Anthropic · Proprietary	1542+7/-7	11,365	$5 / $25	1M
8	313	seed-2.1-pro-preview Bytedance · Proprietary	1539+13/-13	2,577	N/A	N/A
9	612	claude-opus-4-6 Anthropic · Proprietary	1536+6/-6	12,463	$5 / $25	1M
10	613	claude-opus-4-8 Anthropic · Proprietary	1535+10/-10	4,488	$5 / $25	1M
11	615	qwen3.7-max-20260517 Alibaba · Proprietary	1526+10/-10	4,655	$1.25 / $3.75	1M
12	815	glm-5.1 Z.ai · MIT	1523+10/-10	4,589	$1.40 / $4.40	202.8K
13	915	claude-sonnet-4-6 Anthropic · Proprietary	1522+6/-6	14,669	$3 / $15	1M
14	1117	kimi-k2.6 Moonshot · Modified MIT	1514+8/-8	6,851	$0.95 / $4	262.1K
15	1117	gemini-3.5-flash Google · Proprietary	1510+9/-9	5,817	$1.50 / $9	1M
16	1419	minimax-m3 MiniMax · MiniMax Community License	1501+10/-10	4,509	$0.60 / $2.40	N/A
17	1419	gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary	1501+8/-8	7,587	N/A	N/A
18	1620	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1490+7/-7	13,060	$5 / $25	200K
19	1822	gpt-5.5-high (codex-harness) OpenAI · Proprietary	1483+8/-8	7,770	N/A	N/A
20	1624	qwen3.6-max-preview Alibaba · Proprietary	1482+12/-12	2,507	$1.04 / $6.24	262.1K
21	1925	mimo-v2.5-pro Xiaomi · MIT	1473+8/-8	7,887	$0.43 / $0.87	1M
22	1926	kimi-k2.7-code Moonshot · Modified MIT	1471+11/-11	3,315	$0.74 / $3.50	262.1K
23	2026	claude-opus-4-5-20251101 Anthropic · Proprietary	1466+6/-6	15,315	$5 / $25	200K
24	2128	qwen3.6-plus Alibaba · Proprietary	1461+7/-7	9,474	$0.33 / $1.95	1M
25	2033	gpt-5.4-high (codex-harness) OpenAI · Proprietary	1457+17/-17	1,482	$2.50 / $15	1.1M
26	2231	deepseek-v4-pro-thinking DeepSeek · MIT	1457+8/-8	7,330	$0.43 / $0.87	1M
27	2433	gpt-5.5 (codex-harness) OpenAI · Proprietary	1448+8/-8	7,600	N/A	N/A
28	2434	deepseek-v4-pro DeepSeek · MIT	1446+8/-8	6,533	$0.43 / $0.87	1M
29	2533	gemini-3.1-pro-preview Google · Proprietary	1445+6/-6	14,184	$2 / $12	1M
30	2537	glm-4.7 Z.ai · MIT	1440+10/-10	4,882	$0.40 / $1.75	202.8K
31	2637	gemini-3-pro Google · Proprietary	1439+7/-7	17,152	$2 / $12	1M
32	2538	gpt-5.4-medium (codex-harness) OpenAI · Proprietary	1437+16/-16	1,449	$2.50 / $15	1.1M
33	2637	gemini-3-flash Google · Proprietary	1437+7/-7	13,270	$0.50 / $3	1M
34	2937	mimo-v2-pro Xiaomi · Proprietary	1432+8/-8	6,811	$1 / $3	1M
35	3037	kimi-k2.5-thinking Moonshot · Modified MIT	1431+6/-6	13,777	$0.60 / $3	N/A
36	3037	mimo-v2.5 Xiaomi · MIT	1430+8/-8	7,019	$0.10 / $0.28	1M
37	3037	glm-5 Z.ai · MIT	1430+8/-8	7,374	$1 / $3.20	202.8K
38	3847	kimi-k2.5-instant Moonshot · Modified MIT	1408+11/-11	3,611	$0.38 / $2.02	262.1K
39	3849	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1406+12/-12	2,963	$1.75 / $14	400K
40	3753	gpt-5.2 OpenAI · Proprietary	1405+17/-17	1,457	$1.75 / $14	400K
41	3851	gpt-5.4-mini-high OpenAI · Proprietary	1398+7/-7	8,682	$0.75 / $4.50	400K
42	3852	minimax-m2.7 MiniMax · Modified MIT	1396+7/-7	9,230	$0.18 / $0.72	204.8K
43	3851	qwen3.5-397b-a17b Alibaba · Apache 2.0	1396+6/-6	13,069	$0.39 / $2.45	256K
44	3854	gpt-5-medium OpenAI · Proprietary	1395+13/-13	3,756	$1.25 / $10	400K
45	3858	gpt-5.4 OpenAI · Proprietary	1394+22/-22	721	$2.50 / $15	1.1M
46	3853	minimax-m2.1-preview MiniMax · MIT	1391+8/-8	9,273	$0.30 / $1.20	204.8K
47	3854	gpt-5.1-medium OpenAI · Proprietary	1391+9/-9	6,117	$1.25 / $10	400K
48	3954	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1388+7/-7	15,749	$3 / $15	200K
49	4053	gemini-3-flash (thinking-minimal) Google · Proprietary	1387+5/-5	19,843	$0.50 / $3	1M
50	4055	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1386+6/-6	18,414	$3 / $15	200K
51	3956	claude-opus-4-1-20250805 Anthropic · Proprietary	1386+9/-9	8,568	$15 / $75	200K
52	4256	grok-4.20-beta-0309-reasoning xAI · Proprietary	1383+7/-7	10,562	$2 / $6	2M
53	4358	minimax-m2.5 MiniMax · Modified MIT	1381+8/-8	7,856	$0.12 / $0.48	204.8K
54	4963	gemma-4-31b Google · Apache 2.0	1371+9/-9	5,472	$0.14 / $0.40	262.1K
55	4663	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1371+11/-11	3,568	$1.75 / $14	400K
56	5263	deepseek-v3.2-thinking DeepSeek · MIT	1368+8/-8	7,919	$0.23 / $0.34	131.1K
57	5463	qwen3.5-122b-a10b Alibaba · Apache 2.0	1364+7/-7	8,166	$0.26 / $2.08	262.1K
58	5463	grok-4.3 xAI · Proprietary	1363+8/-8	6,838	$1.25 / $2.50	1M
59	5065	hunyuan-hy3-preview Tencent · tencent-hunyuan-community	1362+17/-17	1,352	N/A	N/A
60	5265	gemma-4-26b-a4b Google · Apache 2.0	1359+16/-16	1,508	N/A	N/A
61	5463	qwen3.5-27b Alibaba · Apache 2.0	1356+8/-8	7,673	$0.20 / $1.56	262.1K
62	5464	glm-4.6 Z.ai · MIT	1355+9/-9	8,351	$0.43 / $1.74	202.8K
63	5468	laguna-m.1 Poolside · Proprietary	1351+13/-13	2,552	$0.20 / $0.40	262.1K
64	6070	gpt-5.1 OpenAI · Proprietary	1339+7/-7	12,866	$1.25 / $10	400K
65	6170	mimo-v2-flash (non-thinking) Xiaomi · MIT	1336+8/-8	6,729	$0.10 / $0.30	262.1K
66	6370	gpt-5.2-codex OpenAI · Proprietary	1334+8/-8	7,771	$1.75 / $14	400K
67	6370	deepseek-v3.2 DeepSeek · MIT	1332+7/-7	10,479	$0.23 / $0.34	131.1K
68	6370	gpt-5.1-codex OpenAI · Proprietary	1330+10/-10	6,215	$1.25 / $10	400K
69	6470	kimi-k2-thinking-turbo Moonshot · Modified MIT	1330+6/-6	15,363	$1.15 / $8	262.1K
70	6470	claude-haiku-4-5-20251001 Anthropic · Proprietary	1327+5/-5	23,650	$1 / $5	200K
71	7174	minimax-m2 MiniMax · Apache 2.0	1305+9/-9	8,397	$0.26 / $1.02	204.8K
72	7175	mimo-v2-flash (thinking) Xiaomi · MIT	1301+14/-14	2,098	$0.10 / $0.30	262.1K
73	7175	laguna-xs.2 Poolside · Apache 2.0	1299+12/-12	3,307	$0.10 / $0.20	262.1K
74	7176	deepseek-v3.2-exp DeepSeek · MIT	1288+11/-11	4,874	$0.27 / $0.41	163.8K
75	7276	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1282+7/-7	15,214	$0.40 / $1.60	262.1K
76	7482	mistral-medium-3.5 Mistral · Modified MIT	1269+15/-15	2,030	$1.50 / $7.50	262.1K
77	7683	KAT-Coder-Pro-V1 KwaiKAT · Proprietary	1259+16/-16	1,881	$0.21 / $0.83	256K
78	7682	gemini-3.1-flash-lite-preview Google · Proprietary	1253+7/-7	12,826	$0.25 / $1.50	1M
79	7684	qwen3.5-35b-a3b Alibaba · Apache 2.0	1249+16/-16	1,814	$0.14 / $1	262.1K
80	7685	trinity-large-thinking Arcee AI · Apache 2.0	1243+19/-19	1,313	$0.25 / $0.80	262.1K
81	7685	gpt-5.1-codex-mini OpenAI · Proprietary	1240+17/-17	1,445	$0.25 / $2	400K
82	7685	qwen3.5-flash Alibaba · Proprietary	1237+17/-17	1,560	N/A	N/A
83	7985	grok-4-1-fast-reasoning xAI · Proprietary	1234+9/-9	6,908	$0.20 / $0.50	2M
84	7888	mistral-large-3 Mistral · Apache 2.0	1224+20/-20	1,034	$0.50 / $1.50	N/A
85	8088	grok-4.1-thinking xAI · Proprietary	1209+20/-20	1,209	N/A	N/A
86	8488	gemini-2.5-pro Google · Proprietary	1204+13/-13	3,301	$1.25 / $10	1M
87	8489	granite-4.1-8b IBM · Apache 2.0	1200+18/-18	1,727	$0.05 / $0.10	131.1K
88	8489	devstral-2 Mistral · Modified MIT	1200+17/-17	1,588	N/A	N/A
89	8791	mercury-2 Inception AI · Proprietary	1165+23/-23	948	$0.25 / $0.75	128K
90	8991	grok-4-fast-reasoning xAI · Proprietary	1150+23/-23	933	$0.20 / $0.50	2M
91	8991	grok-code-fast-1 xAI · Proprietary	1140+22/-22	982	$0.20 / $1.50	N/A
92	9292	devstral-medium-2507 Mistral · Proprietary	1092+23/-23	992	$0.40 / $2	128K

Code Arena | WebDev🏆Overall

Remove Style Control Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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

Domain

Code Arena | WebDev🏆Overall

Remove Style Control Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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