Arcada Labs Code Categories Arena 代码能力排行榜

Name: Arcada Labs Code Categories Arena 代码能力排行榜
Creator: DataLearner
License: https://creativecommons.org/licenses/by/4.0/

基于 Arcada Labs Code Categories Arena 用户匿名投票的最新AI大模型代码能力排行榜，通过 Bradley-Terry 模型对 Website、UI Component、Game Dev、Data Visualization 等代码子类别进行综合评分与排名。

榜首模型

Kimi K3

最高得分

1417.00

模型数量

147

数据版本

2026年08月02日

数据来源: Arcada Labs

来源：全部国产模型

榜单历史快照月份:

排名总表

排名	模型名称	得分	95% CI	投票数	机构	许可证
	Kimi K3Moonshot AI	1417.00	+/-11.4	4,230	Moonshot AI	Open Source
	Claude Opus 5Anthropic	1356.00	+/-11.2	4,064	Anthropic	Proprietary
	GPT-5.6 SolOpenAI	1352.00	+/-9.1	6,377	OpenAI	Proprietary
4	GLM-5.2智谱AI	1343.00	+/-6.7	11,968	智谱AI	Open Source
5	Claude Fable 5Anthropic	1342.00	+/-8.3	7,668	Anthropic	Proprietary
6	Claude Opus 4.6Anthropic	1323.00	+/-4.9	24,836	Anthropic	Proprietary
7	Claude Opus 4.6 (thinking)Anthropic	1318.00	+/-5.1	21,528	Anthropic	Proprietary
8	Opus 4.7Anthropic	1318.00	+/-5.3	20,178	Anthropic	Proprietary
9	Gemini 3.6 FlashGoogle	1315.00	+/-8	8,028	Google	Proprietary
10	Grok 4.5xAI	1312.00	+/-6.8	11,519	xAI	Proprietary
11	MiMo-V2.5-ProXiaomi	1309.00	+/-6.6	11,931	Xiaomi	Open Source
12	Qwen3.7 Max阿里巴巴	1308.00	+/-5.4	19,121	阿里巴巴	Proprietary
13	Kimi K2.6Moonshot AI	1307.00	+/-4.7	26,255	Moonshot AI	Open Source
14	Claude Sonnet 4.6Anthropic	1306.00	+/-4.9	24,267	Anthropic	Proprietary
15	GLM 5.1智谱AI	1306.00	+/-6	14,917	智谱AI	Open Source
16	Muse Spark 1.1Facebook AI研究实验室	1303.00	+/-9.2	5,891	Facebook AI研究实验室	Proprietary
17	Claude Sonnet 5Anthropic	1301.00	+/-7.5	9,043	Anthropic	Proprietary
18	GLM-5-Turbo智谱AI	1299.00	+/-4.5	28,910	智谱AI	Proprietary
19	MiMo-V2.5Xiaomi	1291.00	+/-4.3	32,360	Xiaomi	Open Source
20	Kimi K2.7 CodeMoonshot AI	1290.00	+/-6.8	11,053	Moonshot AI	Open Source
21	Qwen3.7-Plus阿里巴巴	1290.00	+/-10.9	4,113	阿里巴巴	Proprietary
22	Gemini 3.5 FlashGoogle Deep Mind	1289.00	+/-5.2	20,164	Google Deep Mind	Proprietary
23	MiniMax M3MiniMaxAI	1285.00	+/-5.9	15,309	MiniMaxAI	Open Source
24	GPT-5.5OpenAI	1284.00	+/-5.4	18,811	OpenAI	Proprietary
25	Muse SparkFacebook AI研究实验室	1281.00	+/-10.9	4,249	Facebook AI研究实验室	Proprietary
26	GLM-5智谱AI	1277.00	+/-3.8	45,314	智谱AI	Open Source
27	DeepSeek-V4-ProDeepSeek-AI	1273.00	+/-5.2	20,232	DeepSeek-AI	Open Source
28	Opus 4.5Anthropic	1272.00	+/-4.1	35,011	Anthropic	Proprietary
29	Claude Opus 4.8Anthropic	1271.00	+/-5.3	19,003	Anthropic	Proprietary
30	Nex N2 ProNex AGI	1271.00	+/-8.3	7,172	Nex AGI	Open Source
31	Gemini 3.1 Pro PreviewGoogle Deep Mind	1271.00	+/-4.9	23,843	Google Deep Mind	Proprietary
32	Kimi K2.5 (thinking)Moonshot AI	1267.00	+/-3.9	41,111	Moonshot AI	Open Source
33	GPT-5.6 TerraOpenAI	1265.00	+/-9.7	5,274	OpenAI	Proprietary
34	MiniMax-M2.7MiniMaxAI	1264.00	+/-4.2	33,180	MiniMaxAI	Open Source
35	Qwen 3.6 Plus Preview阿里巴巴	1264.00	+/-4.6	26,529	阿里巴巴	Proprietary
36	Gemini 3.1 Pro PreviewGoogle Deep Mind	1259.00	+/-4	38,463	Google Deep Mind	Proprietary
37	GLM-5V-Turbo智谱AI	1259.00	+/-4.2	33,892	智谱AI	Proprietary
38	Hy3腾讯AI实验室	1257.00	+/-6.2	13,662	腾讯AI实验室	Open Source
39	GPT-5.6 LunaOpenAI	1252.00	+/-10	4,997	OpenAI	Proprietary
40	Grok 4.20 Beta (Reasoning)xAI	1248.00	+/-4.5	28,838	xAI	Proprietary
41	GLM-4.7智谱AI	1247.00	+/-3.6	46,802	智谱AI	Open Source
42	GPT-5.4 (Design Skill, Medium)OpenAI	1241.00	+/-7.3	9,604	OpenAI	Proprietary
43	GPT-5.4 (medium)OpenAI	1239.00	+/-5.3	18,950	OpenAI	Proprietary
44	InklingThinking Machines Lab	1238.00	+/-12.4	3,183	Thinking Machines Lab	Open Source
45	MiniMax M2.5MiniMaxAI	1237.00	+/-6.7	11,504	MiniMaxAI	Open Source
46	DeepSeek-V4-FlashDeepSeek-AI	1235.00	+/-4.6	27,456	DeepSeek-AI	Open Source
47	Grok 4.20 BetaxAI	1232.00	+/-4.3	31,036	xAI	Proprietary
48	M2.1MiniMaxAI	1220.00	+/-5.1	20,805	MiniMaxAI	Open Source
49	Gemini 3.0 FlashGoogle Deep Mind	1219.00	+/-10.6	4,414	Google Deep Mind	Proprietary
50	Grok 4.3 BetaxAI	1216.00	+/-4.8	23,910	xAI	Proprietary
51	Claude Sonnet 4.5Anthropic	1213.00	+/-3.7	43,705	Anthropic	Proprietary
52	Claude Sonnet 4.5 (thinking)Anthropic	1212.00	+/-3.7	42,668	Anthropic	Proprietary
53	GPT-5.4 (low)OpenAI	1209.00	+/-5.1	21,125	OpenAI	Proprietary
54	Qwen3.5-397B-A17B阿里巴巴	1209.00	+/-7.9	8,131	阿里巴巴	Open Source
55	GPT-5.4 (None)OpenAI	1208.00	+/-4.8	23,583	OpenAI	Proprietary
56	GLM-4.7-Flash智谱AI	1207.00	+/-6.6	11,706	智谱AI	Open Source
57	Claude Sonnet 3.7Anthropic	1206.00	+/-5.9	15,245	Anthropic	Proprietary
58	Hy3 (low)腾讯AI实验室	1206.00	+/-11.2	4,038	腾讯AI实验室	Open Source
59	DeepSeek-V3.1 (thinking)DeepSeek-AI	1205.00	+/-5.7	16,258	DeepSeek-AI	Open Source
60	Step 3.7 FlashStepFunAI	1203.00	+/-5.8	15,834	StepFunAI	Open Source
61	Opus 4.1 (thinking)Anthropic	1201.00	+/-5.8	15,677	Anthropic	Proprietary
62	GPT-5.1 (high)OpenAI	1201.00	+/-5.7	16,056	OpenAI	Proprietary
63	DeepSeek V3.2-ExpDeepSeek-AI	1200.00	+/-5.2	19,490	DeepSeek-AI	Open Source
64	GPT-5.2 (None)OpenAI	1199.00	+/-4.4	28,885	OpenAI	Proprietary
65	GPT-5.2 (medium)OpenAI	1199.00	+/-4.5	27,939	OpenAI	Proprietary
66	GPT-5 (high)OpenAI	1198.00	+/-6.2	13,397	OpenAI	Proprietary
67	GLM-4.6智谱AI	1196.00	+/-5.6	16,911	智谱AI	Open Source
68	Qwen3.5 Plus (0215)阿里巴巴	1196.00	+/-5.4	18,505	阿里巴巴	Proprietary
69	GLM-4.5智谱AI	1195.00	+/-5.2	19,637	智谱AI	Open Source
70	GPT-5 (minimal)OpenAI	1195.00	+/-4.2	32,857	OpenAI	Proprietary
71	GPT-5.2 (low)OpenAI	1195.00	+/-4.6	25,456	OpenAI	Proprietary
72	Opus 4.1Anthropic	1194.00	+/-3.9	39,517	Anthropic	Proprietary
73	DeepSeek V3.2DeepSeek-AI	1194.00	+/-4.4	29,097	DeepSeek-AI	Open Source
74	GPT-5.1 (medium)OpenAI	1191.00	+/-5	21,288	OpenAI	Proprietary
75	Claude Opus 4Anthropic	1190.00	+/-5.6	16,669	Anthropic	Proprietary
76	GPT-5.1 (low)OpenAI	1186.00	+/-4.9	22,157	OpenAI	Proprietary
77	MiMo-V2-FlashXiaomi	1185.00	+/-4.1	35,231	Xiaomi	Open Source
78	Gemini 2.5 ProGoogle Deep Mind	1183.00	+/-8.6	7,044	Google Deep Mind	Proprietary
79	GPT-5.1 CodexOpenAI	1180.00	+/-16.4	1,807	OpenAI	Proprietary
80	GPT-5.1 (None)OpenAI	1180.00	+/-4.9	22,270	OpenAI	Proprietary
81	GPT-5.2 (high)OpenAI	1179.00	+/-10.8	4,167	OpenAI	Proprietary
82	GPT-5.3 CodexOpenAI	1174.00	+/-5.8	15,668	OpenAI	Proprietary
83	Qwen3-Coder-480B-A35B阿里巴巴	1173.00	+/-16.3	1,958	阿里巴巴	Open Source
84	Mistral Large 3MistralAI	1172.00	+/-4.3	30,428	MistralAI	Open Source
85	Claude Sonnet 4Anthropic	1171.00	+/-5.5	17,532	Anthropic	Proprietary
86	DeepSeek-R1-0528DeepSeek-AI	1168.00	+/-5.4	17,944	DeepSeek-AI	Open Source
87	GLM-4.5-Air智谱AI	1167.00	+/-5.5	17,256	智谱AI	Open Source
88	Claude Sonnet 4 (thinking)Anthropic	1166.00	+/-5.7	16,227	Anthropic	Proprietary
89	AGI-01 SwiftLucidQuery	1165.00	+/-20.3	1,233	LucidQuery	Proprietary
90	MiniMax M2MiniMaxAI	1165.00	+/-6.8	10,828	MiniMaxAI	Open Source
91	Nemotron 3 UltraNVIDIA	1156.00	+/-6.7	12,324	NVIDIA	Open Source
92	AesCoder-4BDesignFlow	1154.00	+/-3.9	39,677	DesignFlow	Open Source
93	Mistral Medium 3.5MistralAI	1151.00	+/-7	10,901	MistralAI	Open Source
94	Mistral Medium 3.1 (2508)Mistral	1150.00	+/-4.5	27,678	Mistral	Proprietary
95	Trinity Large ThinkingArcee AI	1147.00	+/-6.5	12,846	Arcee AI	Open Source
96	Haiku 4.5Anthropic	1144.00	+/-4.1	35,511	Anthropic	Proprietary
97	GPT-5-miniOpenAI	1144.00	+/-4	37,061	OpenAI	Proprietary
98	DeepSeek-V3.1DeepSeek-AI	1142.00	+/-5.1	20,278	DeepSeek-AI	Open Source
99	Qwen3-Max-Thinking阿里巴巴	1139.00	+/-4.2	33,357	阿里巴巴	Proprietary
100	DeepSeek-V3-0324DeepSeek-AI	1138.00	+/-5.2	19,257	DeepSeek-AI	Open Source
101	Prime Intellect: INTELLECT-3Prime Intellect	1136.00	+/-4.3	31,349	Prime Intellect	Open Source
102	Gemini 2.5 Flash-Preview-09-2025Google Deep Mind	1134.00	+/-5.3	19,299	Google Deep Mind	Proprietary
103	Grok 4 FastxAI	1130.00	+/-4	36,636	xAI	Proprietary
104	Kimi K2 0905Moonshot AI	1128.00	+/-17.9	1,504	Moonshot AI	Open Source
105	GPT-5.1 Codex MiniOpenAI	1123.00	+/-4.2	33,813	OpenAI	Proprietary
106	Grok 4.1 FastxAI	1122.00	+/-4.2	33,404	xAI	Proprietary
107	Grok 4.1 Fast (reasoning)xAI	1117.00	+/-4.3	31,110	xAI	Proprietary
108	GPT-5-NanoOpenAI	1114.00	+/-8.6	6,710	OpenAI	Proprietary
109	Kimi K2 Turbo PreviewMoonshot AI	1113.00	+/-15.2	2,094	Moonshot AI	Open Source
110	Gemini 2.5 Flash-Lite-Preview-09-2025Google Deep Mind	1111.00	+/-8.5	6,860	Google Deep Mind	Proprietary
111	Gemini 3.1 Flash-LiteGoogle Deep Mind	1101.00	+/-5	23,530	Google Deep Mind	Proprietary
112	Phi-3-medium 14B-previewMicrosoft Azure	1099.00	+/-8.9	6,396	Microsoft Azure	Proprietary
113	Ministral 3 14BMistralAI	1095.00	+/-14.4	2,379	MistralAI	Open Source
114	Gemini 2.5 FlashGoogle Deep Mind	1089.00	+/-8.5	6,960	Google Deep Mind	Proprietary
115	v0-1.5-mdVercel	1086.00	+/-6.9	11,081	Vercel	Proprietary
116	Ministral 3 8BMistralAI	1083.00	+/-14.3	2,427	MistralAI	Open Source
117	Grok 3xAI	1082.00	+/-4.6	26,862	xAI	Proprietary
118	Grok 4 Fast (reasoning)xAI	1080.00	+/-4.1	37,373	xAI	Proprietary
119	Qwen3-235B-A22B-2507阿里巴巴	1068.00	+/-8.6	6,932	阿里巴巴	Open Source
120	Kimi K2Moonshot AI	1063.00	+/-19.5	1,352	Moonshot AI	Open Source
121	Magistral Medium 1.2 (2509)Mistral	1063.00	+/-9.4	5,851	Mistral	Proprietary
122	Qwen3-235B-A22B-Thinking-2507Alibaba	1062.00	+/-9.1	6,169	Alibaba	Open Source
123	GPT-4.1OpenAI	1055.00	+/-17.3	1,747	OpenAI	Proprietary
124	OpenAI o3OpenAI	1049.00	+/-19.5	1,365	OpenAI	Proprietary
125	Grok 4xAI	1046.00	+/-4.9	23,998	xAI	Proprietary
126	Devstral MediumMistralAI	1042.00	+/-8.6	7,158	MistralAI	Proprietary
127	Ministral 3 3B (2512)Mistral	1040.00	+/-13.5	2,852	Mistral	Open Source
128	Codestral 2508Mistral	1037.00	+/-8.8	6,745	Mistral	Proprietary
129	Qwen3-235B-A22B阿里巴巴	1032.00	+/-10.1	5,154	阿里巴巴	Open Source
130	Grok Code Fast 1xAI	1029.00	+/-11.1	4,295	xAI	Proprietary
131	GPT-4.1 miniOpenAI	1023.00	+/-18.3	1,566	OpenAI	Proprietary
132	Mercury 2Inception	1022.00	+/-8.6	10,152	Inception	Proprietary
133	Magistral Small 1.2 (2509)Mistral	1015.00	+/-9.2	6,448	Mistral	Open Source
134	OpenAI o4 - miniOpenAI	1005.00	+/-16.2	2,011	OpenAI	Proprietary
135	Olmo 3.1 32B ThinkAllen AI	1005.00	+/-6.3	16,162	Allen AI	Open Source
136	GPT OSS 120BOpenAI	993.00	+/-10.3	5,268	OpenAI	Open Source
137	GPT-4.1 nanoOpenAI	992.00	+/-16.9	1,901	OpenAI	Proprietary
138	Qwen3-30B-A3B阿里巴巴	971.00	+/-14.6	2,575	阿里巴巴	Open Source
139	Grok 3 minixAI	960.00	+/-8.8	7,626	xAI	Proprietary
140	Llama 3.1 Nemotron Ultra 253BNVIDIA	959.00	+/-13.8	3,172	NVIDIA	Open Source
141	Mistral-Small-3.2MistralAI	937.00	+/-20.8	1,243	MistralAI	Open Source
142	Llama 4 MaverickFacebook AI研究实验室	909.00	+/-18.4	1,678	Facebook AI研究实验室	Open Source
143	Mistral Large 2.1 (2411)Mistral	893.00	+/-21	1,317	Mistral	Proprietary
144	GPT-4oOpenAI	890.00	+/-18.2	1,780	OpenAI	Proprietary
145	Codestral 2 (2501)Mistral	863.00	+/-20.7	1,444	Mistral	Open Source
146	Devstral Small 1.1MistralAI	837.00	+/-22.5	1,250	MistralAI	Open Source
147	Llama 4 ScoutFacebook AI研究实验室	819.00	+/-22.6	1,275	Facebook AI研究实验室	Open Source

数据仅供参考，以官方来源为准。模型名称旁的链接可跳转到 DataLearner 模型详情页。

关于本榜单

本榜单数据来源于Design Arena，由 Y Combinator 支持的 Arcada Labs 开发，是专注于评测 AI 设计代码生成能力的众包匿名对战平台。

与 LMArena 评测通用文本和编程能力不同，Design Arena 的代码榜专门考察模型生成具有视觉呈现效果的前端代码的能力。平台将代码任务细分为 Website、UI 组件、游戏开发、数据可视化、SVG、Web App、移动端等多个子类别，每个子类别均有独立排行。

本页展示的是 Code Categories 综合榜，即将所有子类别的用户投票混合汇总后，统一用 Bradley-Terry 模型（类 Elo 算法）计算出的综合排名。每票等权，不对各子类别做加权处理，因此投票量较大的子类别（如 Website）对综合分数的影响更大。得分越高，代表模型在设计代码生成场景下的综合人类偏好越强。

常见问题 (FAQ)

什么是 Arcada Labs Code Categories Arena？

Arcada Labs Code Categories Arena 是专注于设计代码生成能力的匿名评测平台，覆盖 Website、UI 组件、游戏开发、数据可视化等多个代码生成子类别，并将投票汇总为综合榜单。

Arcada Code Arena 与 LMArena Coding Arena 有什么区别？

LMArena Coding Arena 主要评测通用编程能力，例如代码生成、调试和算法实现；Arcada Code Arena 专注于具有视觉呈现效果的前端设计代码，例如 HTML 页面、交互 UI、图表、SVG 和原型。

排名方法论是什么？

Arcada Labs 将各代码子类别的原始投票混合后运行 Bradley-Terry 模型。每票等权，不按子类别单独加权，因此投票量较大的子类别会对综合分数产生更大影响。

哪类模型在设计代码场景表现更好？

具备强视觉理解和前端代码生成能力的大模型通常表现更好。针对 UI 和代码生成优化的专项模型，在布局、交互和视觉细节任务上也可能有突出表现。