Code Arena | WebDevHTML

View overall rankings across AI models on front-end web development tasks: multi-step reasoning, tool use, and HTML code generation.

Jun 16, 2026

144,876 votes

88 models

Rank by

	Rank Spread
1	11	claude-fable-5 Anthropic · Proprietary	1665+41/-41	301	$10 / $50	1M
2	211	claude-opus-4-7 Anthropic · Proprietary	1559+22/-22	841	$5 / $25	1M
3	214	claude-opus-4-8-thinking Anthropic · Proprietary	1555+34/-34	370	$5 / $25	1M
4	217	glm-5.2 (max) Z.ai · MIT	1555+40/-40	246	$1.40 / $4.40	1M
5	211	claude-opus-4-7-thinking Anthropic · Proprietary	1552+21/-21	968	$5 / $25	1M
6	212	claude-opus-4-6 Anthropic · Proprietary	1545+16/-16	1,541	$5 / $25	1M
7	213	claude-opus-4-6-thinking Anthropic · Proprietary	1542+17/-17	1,442	$5 / $25	1M
8	220	glm-5.1 Z.ai · MIT	1532+28/-28	527	$1.40 / $4.40	202.8K
9	221	qwen3.7-max-20260517 Alibaba · Proprietary	1530+29/-29	449	$1.25 / $3.75	1M
10	221	gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary	1523+23/-23	778	N/A	N/A
11	222	claude-opus-4-8 Anthropic · Proprietary	1523+29/-29	437	$5 / $25	1M
12	521	claude-sonnet-4-6 Anthropic · Proprietary	1514+14/-14	1,823	$3 / $15	1M
13	423	gpt-5.5-high (codex-harness) OpenAI · Proprietary	1507+22/-22	791	N/A	N/A
14	822	claude-opus-4-5-20251101-thinking-32k Anthropic · Proprietary	1503+11/-11	7,949	$5 / $25	200K
15	627	kimi-k2.6 Moonshot · Modified MIT	1499+22/-22	732	$0.95 / $4	262.1K
16	729	gpt-5.5 (codex-harness) OpenAI · Proprietary	1493+22/-22	820	N/A	N/A
17	929	gemini-3.1-pro-preview Google · Proprietary	1487+16/-16	1,526	$2 / $12	1M
18	734	gemini-3.5-flash Google · Proprietary	1484+35/-35	323	$1.50 / $9	1M
19	835	qwen3.6-max-preview Alibaba · Proprietary	1475+34/-34	310	$1.04 / $6.24	262.1K
20	1529	claude-opus-4-5-20251101 Anthropic · Proprietary	1474+10/-10	8,384	$5 / $25	200K
21	1233	mimo-v2.5-pro Xiaomi · MIT	1473+22/-22	768	$0.43 / $0.87	1M
22	739	gpt-5.4-medium (codex-harness) OpenAI · Proprietary	1472+48/-48	165	$2.50 / $15	1.1M
23	1534	qwen3.6-plus Alibaba · Proprietary	1465+19/-19	1,029	$0.33 / $1.95	1M
24	1632	gemini-3-pro Google · Proprietary	1462+10/-10	13,755	$2 / $12	1M
25	1535	deepseek-v4-pro-thinking DeepSeek · MIT	1462+22/-22	759	$0.43 / $0.87	1M
26	845	gpt-5.4-high (codex-harness) OpenAI · Proprietary	1456+49/-49	160	$2.50 / $15	1.1M
27	1440	kimi-k2.7-code Moonshot · Modified MIT	1453+34/-34	290	$0.61 / $3.07	262.1K
28	1540	minimax-m3 MiniMax · Proprietary	1453+33/-33	356	$0.60 / $2.40	N/A
29	1639	glm-5 Z.ai · MIT	1450+22/-22	807	$1 / $3.20	202.8K
30	1938	glm-4.7 Z.ai · MIT	1449+11/-11	4,755	$0.40 / $1.75	202.8K
31	2139	gemini-3-flash Google · Proprietary	1440+10/-10	9,253	$0.50 / $3	1M
32	1940	mimo-v2-pro Xiaomi · Proprietary	1438+21/-21	795	$1 / $3	1M
33	1951	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1426+30/-30	395	$1.75 / $14	400K
34	2544	kimi-k2.5-thinking Moonshot · Modified MIT	1424+14/-14	1,797	$0.60 / $3	N/A
35	2351	mimo-v2.5 Xiaomi · MIT	1420+23/-23	695	$0.14 / $0.28	1M
36	2054	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1419+32/-32	360	$1.75 / $14	400K
37	2551	gpt-5.4-mini-high OpenAI · Proprietary	1417+21/-21	920	$0.75 / $4.50	400K
38	2553	kimi-k2.5-instant Moonshot · Modified MIT	1413+25/-25	590	$0.38 / $2.02	262.1K
39	2651	gpt-5.2 OpenAI · Proprietary	1413+17/-17	1,457	$1.75 / $14	400K
40	3252	minimax-m2.1-preview MiniMax · MIT	1404+11/-11	6,777	$0.29 / $0.95	204.8K
41	2954	minimax-m2.5 MiniMax · Modified MIT	1404+19/-19	1,032	$0.15 / $0.90	204.8K
42	3253	gpt-5-medium OpenAI · Proprietary	1402+14/-14	3,755	$1.25 / $10	400K
43	3254	qwen3.5-397b-a17b Alibaba · Apache 2.0	1400+15/-15	1,502	$0.39 / $2.45	256K
44	3353	gpt-5.1-medium OpenAI · Proprietary	1399+11/-11	6,094	$1.25 / $10	400K
45	3256	minimax-m2.7 MiniMax · Modified MIT	1398+19/-19	988	$0.25 / $1	204.8K
46	3453	gemini-3-flash (thinking-minimal) Google · Proprietary	1397+10/-10	6,753	$0.50 / $3	1M
47	3454	claude-sonnet-4-5-20250929-thinking-32k Anthropic · Proprietary	1396+9/-9	11,310	$3 / $15	200K
48	3456	claude-opus-4-1-20250805 Anthropic · Proprietary	1393+10/-10	8,549	$15 / $75	200K
49	3856	claude-sonnet-4-5-20250929 Anthropic · Proprietary	1386+9/-9	12,952	$3 / $15	200K
50	3462	qwen3.5-27b Alibaba · Apache 2.0	1383+20/-20	932	$0.20 / $1.56	262.1K
51	3962	grok-4.20-beta-0309-reasoning xAI · Proprietary	1373+18/-18	1,111	$2 / $6	2M
52	4762	deepseek-v3.2-thinking DeepSeek · MIT	1372+12/-12	3,998	$0.23 / $0.34	131.1K
53	5062	glm-4.6 Z.ai · MIT	1363+10/-10	8,318	$0.43 / $1.74	202.8K
54	5065	mimo-v2-flash (non-thinking) Xiaomi · MIT	1362+12/-12	4,111	$0.10 / $0.30	262.1K
55	4368	gemma-4-31b Google · Apache 2.0	1360+27/-27	526	$0.14 / $0.40	262.1K
56	5065	gpt-5.1 OpenAI · Proprietary	1360+10/-10	10,005	$1.25 / $10	400K
57	4768	grok-4.3 xAI · Proprietary	1360+24/-24	688	$1.25 / $2.50	1M
58	3473	gemma-4-26b-a4b Google · Apache 2.0	1356+44/-44	204	N/A	N/A
59	3473	hunyuan-hy3-preview Tencent · tencent-hunyuan-community	1355+44/-44	190	N/A	N/A
60	5068	mimo-v2-flash (thinking) Xiaomi · MIT	1349+19/-19	1,185	$0.10 / $0.30	262.1K
61	5068	qwen3.5-122b-a10b Alibaba · Apache 2.0	1348+19/-19	992	$0.26 / $2.08	262.1K
62	5469	gpt-5.2-codex OpenAI · Proprietary	1340+13/-13	3,136	$1.75 / $14	400K
63	5669	gpt-5.1-codex OpenAI · Proprietary	1337+11/-11	6,199	$1.25 / $10	400K
64	5669	kimi-k2-thinking-turbo Moonshot · Modified MIT	1336+9/-9	9,966	$1.15 / $8	262.1K
65	5079	laguna-m.1 Poolside · Proprietary	1319+45/-45	183	$0.20 / $0.40	262.1K
66	5477	qwen3.5-35b-a3b Alibaba · Apache 2.0	1316+37/-37	251	$0.14 / $1	262.1K
67	6374	claude-haiku-4-5-20251001 Anthropic · Proprietary	1314+9/-9	11,887	$1 / $5	200K
68	6374	minimax-m2 MiniMax · Apache 2.0	1312+10/-10	8,370	$0.26 / $1	204.8K
69	5480	mistral-medium-3.5 Mistral · Modified MIT	1309+43/-43	231	$1.50 / $7.50	262.1K
70	6375	deepseek-v3.2 DeepSeek · MIT	1307+11/-11	5,251	$0.23 / $0.34	131.1K
71	5680	qwen3.5-flash Alibaba · Proprietary	1305+43/-43	196	N/A	N/A
72	6576	deepseek-v3.2-exp DeepSeek · MIT	1295+12/-12	4,872	$0.27 / $0.41	163.8K
73	6777	qwen3-coder-480b-a35b-instruct Alibaba · Apache 2.0	1291+9/-9	10,765	$0.40 / $1.60	262.1K
74	6082	laguna-xs.2 Poolside · Apache 2.0	1287+41/-41	253	$0.10 / $0.20	262.1K
75	6384	trinity-large-thinking Arcee AI · Apache 2.0	1273+46/-46	196	$0.25 / $0.80	262.1K
76	6881	gemini-3.1-flash-lite-preview Google · Proprietary	1269+18/-18	1,358	$0.25 / $1.50	1M
77	6981	KAT-Coder-Pro-V1 KwaiKAT · Proprietary	1267+16/-16	1,881	$0.21 / $0.83	256K
78	7284	gpt-5.1-codex-mini OpenAI · Proprietary	1248+18/-18	1,444	$0.25 / $2	400K
79	7484	grok-4-1-fast-reasoning xAI · Proprietary	1244+12/-12	5,453	$0.20 / $0.50	2M
80	7685	mistral-large-3 Mistral · Apache 2.0	1229+21/-21	1,032	$0.50 / $1.50	N/A
81	7185	granite-4.1-8b IBM · Apache 2.0	1229+47/-47	229	$0.05 / $0.10	131.1K
82	7785	grok-4.1-thinking xAI · Proprietary	1217+20/-20	1,209	N/A	N/A
83	7785	devstral-2 Mistral · Modified MIT	1215+19/-19	1,346	N/A	N/A
84	8085	gemini-2.5-pro Google · Proprietary	1211+14/-14	3,299	$1.25 / $10	1M
85	7187	mercury-2 Inception AI · Proprietary	1206+70/-70	100	$0.25 / $0.75	128K
86	8587	grok-4-fast-reasoning xAI · Proprietary	1157+24/-24	934	$0.20 / $0.50	2M
87	8587	grok-code-fast-1 xAI · Proprietary	1146+23/-23	981	$0.20 / $1.50	N/A
88	8888	devstral-medium-2507 Mistral · Proprietary	1097+23/-23	992	$0.40 / $2	128K

Code Arena | WebDevHTML

Remove Style Control Leaderboard Plots

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

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)

Domain

Code Arena | WebDevHTML

Remove Style Control Leaderboard Plots

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

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)