WebDev Arena: Best AI for Web Development

	Rank Spread
1	11	Claude Opus 5.5 (Max) Anthropic · Proprietary	1807+14/-14	2,775	$4 / $20	1M
2	24	GPT-6 Astra (Max) OpenAI · Proprietary	1777+10/-10	6,014	$10 / $50	1.1M
3	24	Claude Sonnet 5.5 (xHigh) Anthropic · Proprietary	1768+13/-13	3,182	$2 / $10	1M
4	25	GPT-6.1 Sol (Max) OpenAI · Proprietary	1755+13/-13	2,863	$2 / $10	1.1M
5	45	Claude Fable 5.1 (Max) Anthropic · Proprietary	1741+9/-9	7,503	$10 / $50	1M
6	66	Claude Sonnet 5.5 (High) Anthropic · Proprietary	1711+10/-10	4,914	$2 / $10	1M
7	710	Claude Opus 5 (Max) Anthropic · Proprietary	1689+6/-6	18,310	$5 / $25	1M
8	711	GPT-6 Sol (Max) OpenAI · Proprietary	1683+11/-11	4,364	$2 / $10	1.1M
9	713	Gemini 4 Argon (High) Google · Proprietary	1678+15/-15	1,775	$2 / $10	1M
10	811	Qwen3.8-Max (0902) Alibaba · Proprietary	1674+7/-7	13,812	$2 / $6	N/A
11	715	Qwen3.8-Max Alibaba · Proprietary	1672+12/-12	3,440	$2 / $6	1M
12	1015	Muse Spark 1.3 (Max) Meta · Proprietary	1658+8/-8	9,068	$1.25 / $4.25	1M
13	1115	Claude Opus 5 (High) Anthropic · Proprietary	1657+5/-5	24,211	$5 / $25	1M
14	1115	Kimi K3 (Max) Moonshot · Kimi K3 license	1655+6/-6	19,220	$3 / $15	1M
15	1019	Muse Wonder (Max) Meta · Proprietary	1650+15/-15	1,942	$4 / $20	1M
16	1523	Grok 4.7 (xHigh) SpaceXAI · Proprietary	1639+10/-10	5,021	$2 / $6	500K
17	1525	MiMo-V2.6-Flash Xiaomi · MIT	1634+10/-10	5,016	$0.14 / $0.28	1.1M
18	1526	Hy4 preview Tencent · Apache 2.0	1631+10/-10	4,802	$0.75 / $2.25	1M
19	1525	Qwen3.8-Flash-Next Alibaba · qwen-community-1.0	1630+8/-8	8,083	$0.16 / $0.47	1M
20	1626	MiMo-V2.6-Pro Xiaomi · MIT	1625+10/-10	4,763	$0.43 / $0.87	1.1M
21	1626	Claude Fable 5 (High) Anthropic · Proprietary	1625+6/-6	15,612	$10 / $50	1M
22	1626	Muse Spark 1.3 (xHigh) Meta · Proprietary	1622+8/-8	8,436	$1.25 / $4.25	1M
23	1726	GLM-5.3 (Max) Z.ai · MIT	1621+8/-8	9,542	$1.40 / $4.40	1M
24	1628	DeepSeek-V4.1-Flash (Max) DeepSeek · MIT	1618+11/-11	3,540	$0.30 / $1.20	1M
25	1728	Grok 4.6 (High) SpaceXAI · Proprietary	1617+7/-7	10,179	$2 / $6	500K
26	1928	GPT-5.6 Sol (xHigh, Codex Harness) OpenAI · Proprietary	1616+6/-6	17,605	$4 / $20	1.1M
27	2429	GLM-5.3-Flash Z.ai · MIT	1605+7/-7	17,579	$0.05 / $0.18	1M
28	2429	GLM-5.2 (Max) Z.ai · MIT	1605+6/-6	16,407	$1.40 / $4.40	1M
29	2734	Qwen3.8-27B Alibaba · Apache 2.0	1593+7/-7	15,940	$0.40 / $3	N/A
30	2935	Gemini 3.7 Flash (High) Google · Proprietary	1591+7/-7	12,258	$0.75 / $3.75	1M
31	2935	Gemini 3.8 Flash (High) Google · Proprietary	1585+7/-7	10,514	$0.75 / $3.75	1M
32	2936	Claude Haiku 5.5 (High) Anthropic · Proprietary	1585+11/-11	3,156	$0.10 / $0.50	1M
33	2936	DeepSeek-V4-Pro (High, 20260813) DeepSeek · MIT	1582+9/-9	4,728	$1.32 / $3.96	N/A
34	2936	DeepSeek-V4-Flash (High) DeepSeek · MIT	1581+9/-9	4,963	$0.30 / $1.20	1M
35	3036	GPT-6 Luna (Max) OpenAI · Proprietary	1578+6/-6	20,045	$0.10 / $0.50	1.1M
36	3241	Step 5 Preview (High) StepFun · Proprietary	1565+10/-10	4,424	$1 / $2.70	1M
37	3642	Claude Opus 4.7 (High) Anthropic · Proprietary	1558+6/-6	17,932	$5 / $25	1M
38	3643	Claude Opus 4.7 Anthropic · Proprietary	1556+6/-6	18,244	$5 / $25	1M
39	3643	Claude Opus 4.8 (High) Anthropic · Proprietary	1556+6/-6	18,519	$5 / $25	1M
40	3645	Grok 4.5 SpaceXAI · Proprietary	1553+7/-7	11,098	$2 / $6	500K
41	3748	Claude Opus 4.6 (High) Anthropic · Proprietary	1547+5/-5	19,402	$5 / $25	1M
42	3848	Muse Spark 1.1 Meta · Proprietary	1542+8/-8	7,990	$1.25 / $4.25	N/A
43	3649	Mistral Large 4 Mistral · Proprietary	1542+13/-13	2,536	$0.68 / $2.09	1M
44	4048	Claude Sonnet 5 (High) Anthropic · Proprietary	1541+6/-6	15,495	$2 / $10	1M
45	4149	Gemini 3.6 Flash (High) Google · Proprietary	1538+7/-7	8,758	$0.75 / $3.75	1M
46	4148	Claude Opus 4.6 Anthropic · Proprietary	1537+5/-5	20,659	$5 / $25	1M
47	4149	Claude Opus 4.8 Anthropic · Proprietary	1536+6/-6	17,426	$5 / $25	1M
48	4054	Muse Spark 1.2 (xHigh) Meta · Proprietary	1534+14/-14	2,162	$1.25 / $4.25	N/A
49	4856	Claude Sonnet 4.6 Anthropic · Proprietary	1523+5/-5	22,841	$1.50 / $7.50	1M
50	4857	GPT-5.6 Terra (xHigh, Codex Harness) OpenAI · Proprietary	1522+6/-6	13,678	$2 / $12	1M
51	4858	Seed2.1 Pro Preview Bytedance · Proprietary	1520+6/-6	14,893	$0.88 / $4.42	262.1K
52	4859	GPT-5.6 Luna (xHigh, Codex Harness) OpenAI · Proprietary	1519+6/-6	12,646	$0.20 / $1.20	1M
53	4859	Qwen3.7-Max (20260517) Alibaba · Proprietary	1515+7/-7	8,892	$1.48 / $4.42	1M
54	4960	GPT-5.5 (xHigh, Codex Harness) OpenAI · Proprietary	1513+6/-6	15,655	$5 / $30	N/A
55	4564	Muse Spark Open (Max) Meta · muse-model-license	1511+20/-20	991	$1.25 / $4.25	1M
56	5060	Kimi K2.6 Moonshot · Modified MIT	1510+7/-7	10,166	$0.95 / $4	262.1K
57	5161	GLM-5.1 Z.ai · MIT	1508+7/-7	10,715	$1.40 / $4.40	202.8K
58	5262	Hy3 Tencent · Apache 2.0	1506+8/-8	6,168	$0.08 / $0.33	262.1K
59	4964	gemini-3.5-flash Google · Proprietary	1504+15/-15	1,821	$0.75 / $4.50	1M
60	5464	Gemini 3.5 Flash (High) Google · Proprietary	1500+7/-7	9,400	$0.75 / $4.50	1M
61	5666	Claude Opus 4.5 (High, 32K, 20251101) Anthropic · Proprietary	1494+8/-8	11,030	$5 / $25	200K
62	5766	Gemini 3.5 Flash (Medium) Google · Proprietary	1491+7/-7	12,158	$0.75 / $4.50	1M
63	5869	GPT-5.5 (High, Codex Harness) OpenAI · Proprietary	1487+6/-6	17,970	$5 / $30	N/A
64	5871	Qwen3.6-Max-Preview Alibaba · Proprietary	1483+13/-13	2,711	$1.27 / $7.61	262.1K
65	6169	MiniMax-M3 MiniMax · MiniMax Community License	1482+6/-6	19,499	$0.30 / $1.20	524.3K
66	6170	MiMo-V2.5-Pro Xiaomi · MIT	1481+5/-5	22,166	$0.43 / $0.87	1.1M
67	6372	Kimi K2.7 Code Moonshot · Modified MIT	1474+9/-9	4,966	$0.67 / $3.35	262.1K
68	6572	Claude Opus 4.5 (20251101) Anthropic · Proprietary	1469+7/-7	13,418	$5 / $25	200K
69	6674	DeepSeek-V4-Pro Preview (High) DeepSeek · MIT	1464+6/-6	13,175	$1.32 / $3.96	1M
70	6380	GPT-5.4 (High, Codex Harness) OpenAI · Proprietary	1464+19/-19	1,349	$2.50 / $15	1.1M
71	6774	Qwen3.6-Plus Alibaba · Proprietary	1462+6/-6	18,599	$0.33 / $1.95	1M
72	6977	GPT-5.5 (Codex Harness) OpenAI · Proprietary	1456+6/-6	15,887	$5 / $30	N/A
73	7184	DeepSeek-V4-Pro DeepSeek · MIT	1447+6/-6	13,984	$1.32 / $3.96	1M
74	7184	Gemini 3.1 Pro Preview Google · Proprietary	1447+5/-5	24,223	$1 / $6	1M
75	6987	GPT-5.4 (Medium, Codex Harness) OpenAI · Proprietary	1444+18/-18	1,376	$2.50 / $15	1.1M
76	6399	Gemini 3.5 Flash-Lite Google · Proprietary	1441+41/-41	241	$0.15 / $1.25	1M
77	7287	Gemini 3 Pro Google · Proprietary	1440+8/-8	14,092	$2 / $12	1M
78	7287	Gemini 3 Flash Google · Proprietary	1440+9/-9	10,890	$0.50 / $3	1M
79	7387	MiMo-V2.5 Xiaomi · MIT	1438+6/-6	14,915	$0.14 / $0.28	1.1M
80	7187	beam-1.0-501b-a23b Reflection · Apache 2.0	1438+13/-13	2,908	$1 / $3	1M
81	7387	Kimi K2.5 (Thinking) Moonshot · Modified MIT	1437+5/-5	20,099	$0.60 / $3	N/A
82	7387	GLM-5 Z.ai · MIT	1435+8/-8	7,496	$1 / $3.20	202.8K
83	7287	GLM-4.7 Z.ai · MIT	1435+12/-12	4,007	$0.60 / $2.20	204.8K
84	7387	MiMo-V2-Pro Xiaomi · Proprietary	1434+8/-8	7,245	$1.10 / $3.30	1M
85	7587	DeepSeek-V4-Flash Preview (High) DeepSeek · MIT	1431+7/-7	10,114	$0.30 / $1.20	1M
86	7597	GPT-5 (Medium) OpenAI · Proprietary	1418+16/-16	3,092	$1.25 / $10	400K
87	75100	GPT-5.2 OpenAI · Proprietary	1417+23/-23	1,081	$0.88 / $7	400K
88	8593	Inkling Thinky · Apache 2.0	1414+6/-6	15,505	$1 / $4.05	524.3K
89	8599	Inkling-Small Thinky · Apache 2.0	1409+9/-9	5,339	$0.45 / $1.20	524.3K
90	85101	GPT-5.3-Codex (Codex Harness) OpenAI · Proprietary	1407+14/-14	2,641	$1.75 / $14	400K
91	85101	Kimi K2.5 (Instant) Moonshot · Modified MIT	1405+12/-12	3,264	$0.50 / $2.50	262.1K
92	85102	GPT-5.4 OpenAI · Proprietary	1402+10/-10	4,074	$2.50 / $15	1.1M
93	85103	GLM-5V-Turbo Z.ai · Proprietary	1402+13/-13	2,405	$1.20 / $4	202.8K
94	8699	Qwen3.5-397B-A17B Alibaba · Apache 2.0	1400+5/-5	21,161	$0.50 / $3.60	262.1K
95	86101	MiniMax-M2.7 MiniMax · Modified MIT	1399+6/-6	15,981	$0.30 / $1.20	204.8K
96	86102	GPT-5.4 mini (High) OpenAI · Proprietary	1398+7/-7	11,944	$0.75 / $4.50	400K
97	86103	GPT-5.1 (Medium) OpenAI · Proprietary	1396+12/-12	4,910	$0.63 / $5	400K
98	87103	Claude Sonnet 4.5 (High, 32K, 20250929) Anthropic · Proprietary	1394+8/-8	13,251	$3 / $15	200K
99	87106	Claude Opus 4.1 (20250805) Anthropic · Proprietary	1390+11/-11	6,927	$7.50 / $37.50	200K
100	90106	MiniMax-M2.5 MiniMax · Modified MIT	1386+8/-8	7,623	$0.27 / $0.95	204.8K
101	94106	Claude Sonnet 4.5 (20250929) Anthropic · Proprietary	1385+7/-7	15,723	$3 / $15	1M
102	96106	Gemini 3 Flash (Minimal) Google · Proprietary	1385+5/-5	22,155	$0.50 / $3	1M
103	91107	MiniMax-M2.1 Preview MiniMax · MIT	1384+10/-10	7,639	$0.30 / $1.20	204.8K
104	99111	Grok 4.20 Beta (Reasoning, 0309) SpaceXAI · Proprietary	1376+6/-6	15,455	$1.25 / $2.50	1M
105	99114	GPT-5.3-Codex (Codex Harness) OpenAI · Proprietary	1371+11/-11	3,656	$1.75 / $14	400K
106	99114	Solar Pro 4 Upstage · Proprietary	1371+10/-10	4,660	$0.09 / $0.36	524.3K
107	104114	Gemma 4 31B Google · Apache 2.0	1367+6/-6	14,490	$0.99 / $1.49	131.1K
108	104115	DeepSeek-V3.2 (Thinking) DeepSeek · MIT	1362+9/-9	6,915	$0.28 / $0.42	163.8K
109	105115	Qwen3.5-122B-A10B Alibaba · Apache 2.0	1361+8/-8	8,241	$0.26 / $2.08	262.1K
110	103119	Gemma 4 26B A4B Google · Apache 2.0	1359+17/-17	1,502	N/A	N/A
111	105116	Qwen3.5-27B Alibaba · Apache 2.0	1358+8/-8	7,782	$0.26 / $2.60	262.1K
112	105116	Grok 4.3 SpaceXAI · Proprietary	1358+6/-6	14,966	$1.25 / $2.50	1M
113	104120	Hy3 preview Tencent · tencent-hunyuan-community	1357+17/-17	1,447	$0.18 / $0.60	262.1K
114	104120	Muse Glimmer Meta · Apache-2.0	1355+16/-16	1,647	N/A	N/A
115	108119	Laguna M.1 Poolside · Apache 2.0	1350+9/-9	5,396	$0.20 / $0.40	262.1K
116	112122	GPT-5.1 OpenAI · Proprietary	1342+8/-8	10,711	$0.63 / $5	400K
117	110122	GLM-4.6 Z.ai · MIT	1341+11/-11	6,781	$0.50 / $2	204.8K
118	112122	GPT-5.2-Codex OpenAI · Proprietary	1339+9/-9	6,720	$1.75 / $14	400K
119	112123	GPT-5.1-Codex OpenAI · Proprietary	1337+12/-12	5,007	$1.25 / $10	400K
120	114123	MiMo-V2-Flash (Non-Thinking) Xiaomi · MIT	1330+10/-10	5,689	$0.10 / $0.30	262.1K
121	116123	Claude Haiku 4.5 (20251001) Anthropic · Proprietary	1330+5/-5	29,088	$1 / $5	200K
122	116123	DeepSeek-V3.2 DeepSeek · MIT	1326+8/-8	9,382	$0.28 / $0.42	163.8K
123	119123	Kimi K2 Thinking Turbo Moonshot · Modified MIT	1322+7/-7	13,093	$0.57 / $2.30	131.1K
124	124126	Laguna XS.2 Poolside · Apache 2.0	1302+11/-11	4,231	$0.10 / $0.20	262.1K
125	124126	MiniMax-M2 MiniMax · Apache 2.0	1297+11/-11	6,713	$0.30 / $1.20	204.8K
126	124129	MiMo-V2-Flash (Thinking) Xiaomi · MIT	1293+16/-16	1,686	$0.10 / $0.30	262.1K
127	126131	Qwen3-Coder-480B-A35B-Instruct Alibaba · Apache 2.0	1275+8/-8	12,712	$0.65 / $3.25	1M
128	126134	DeepSeek-V3.2-Exp DeepSeek · MIT	1272+14/-14	3,969	$0.27 / $0.41	163.8K
129	126137	Mistral Medium 3.5 Mistral · Modified MIT	1264+15/-15	2,320	$0.75 / $3.75	262.1K
130	128137	Gemini 3.1 Flash-Lite Preview Google · Proprietary	1257+7/-7	14,389	$0.25 / $1.50	1M
131	127139	KAT-Coder-Pro V1 Proprietary	1256+19/-19	1,504	$0.21 / $0.83	256K
132	127139	Qwen3.5-35B-A3B Alibaba · Apache 2.0	1254+17/-17	1,617	$0.15 / $1	262.1K
133	128139	Qwen3.5-Flash Alibaba · Proprietary	1244+20/-20	1,329	N/A	N/A
134	128139	GPT-5.1-Codex-Mini OpenAI · Proprietary	1244+22/-22	1,154	$0.25 / $2	400K
135	129139	Grok 4.1 Fast (Reasoning) SpaceXAI · Proprietary	1242+11/-11	5,489	$0.20 / $0.50	128K
136	129139	Trinity Large Thinking Apache 2.0	1238+20/-20	1,361	$0.25 / $0.80	262.1K
137	129141	Mistral Large 3 Mistral · Apache 2.0	1230+25/-25	839	$0.50 / $1.50	N/A
138	131141	Gemini 2.5 Pro Google · Proprietary	1226+16/-16	2,730	$1.25 / $10	1M
139	131143	Grok 4.1 (Thinking) SpaceXAI · Proprietary	1215+25/-25	961	N/A	N/A
140	137144	Devstral 2 Mistral · Modified MIT	1197+21/-21	1,182	N/A	N/A
141	137144	Granite 4.1 8B IBM · Apache 2.0	1193+18/-18	1,772	$0.05 / $0.10	131.1K
142	139144	Mercury 2 Inception AI · Proprietary	1171+24/-24	955	$0.25 / $0.75	128K
143	139144	Grok Code Fast 1 SpaceXAI · Proprietary	1166+28/-28	789	$0.20 / $1.50	N/A
144	140144	Grok 4 Fast (Reasoning) SpaceXAI · Proprietary	1159+27/-27	742	$0.20 / $0.50	N/A
145	145145	Devstral Medium (2507) Mistral · Proprietary	1071+31/-31	842	$0.40 / $2	128K

Rank Spread

Claude Opus 5.5 (Max)

Anthropic · Proprietary

1807+14/-14

2,775

$4 / $20

GPT-6 Astra (Max)

OpenAI · Proprietary

1777+10/-10

6,014

$10 / $50

1.1M

Claude Sonnet 5.5 (xHigh)

Anthropic · Proprietary

1768+13/-13

3,182

$2 / $10

GPT-6.1 Sol (Max)

OpenAI · Proprietary

1755+13/-13

2,863

$2 / $10

1.1M

Claude Fable 5.1 (Max)

Anthropic · Proprietary

1741+9/-9

7,503

$10 / $50

Claude Sonnet 5.5 (High)

Anthropic · Proprietary

1711+10/-10

4,914

$2 / $10

710

Claude Opus 5 (Max)

Anthropic · Proprietary

1689+6/-6

18,310

$5 / $25

711

GPT-6 Sol (Max)

OpenAI · Proprietary

1683+11/-11

4,364

$2 / $10

1.1M

713

Gemini 4 Argon (High)

Google · Proprietary

1678+15/-15

1,775

$2 / $10

811

Qwen3.8-Max (0902)

Alibaba · Proprietary

1674+7/-7

13,812

$2 / $6

N/A

715

Qwen3.8-Max

Alibaba · Proprietary

1672+12/-12

3,440

$2 / $6

1015

Muse Spark 1.3 (Max)

Meta · Proprietary

1658+8/-8

9,068

$1.25 / $4.25

1115

Claude Opus 5 (High)

Anthropic · Proprietary

1657+5/-5

24,211

$5 / $25

1115

Kimi K3 (Max)

Moonshot · Kimi K3 license

1655+6/-6

19,220

$3 / $15

1019

Muse Wonder (Max)

Meta · Proprietary

1650+15/-15

1,942

$4 / $20

1523

Grok 4.7 (xHigh)

SpaceXAI · Proprietary

1639+10/-10

5,021

$2 / $6

500K

1525

MiMo-V2.6-Flash

Xiaomi · MIT

1634+10/-10

5,016

$0.14 / $0.28

1.1M

1526

Hy4 preview

Tencent · Apache 2.0

1631+10/-10

4,802

$0.75 / $2.25

1525

Qwen3.8-Flash-Next

Alibaba · qwen-community-1.0

1630+8/-8

8,083

$0.16 / $0.47

1626

MiMo-V2.6-Pro

Xiaomi · MIT

1625+10/-10

4,763

$0.43 / $0.87

1.1M

1626

Claude Fable 5 (High)

Anthropic · Proprietary

1625+6/-6

15,612

$10 / $50

1626

Muse Spark 1.3 (xHigh)

Meta · Proprietary

1622+8/-8

8,436

$1.25 / $4.25

1726

GLM-5.3 (Max)

Z.ai · MIT

1621+8/-8

9,542

$1.40 / $4.40

1628

DeepSeek-V4.1-Flash (Max)

DeepSeek · MIT

1618+11/-11

3,540

$0.30 / $1.20

1728

Grok 4.6 (High)

SpaceXAI · Proprietary

1617+7/-7

10,179

$2 / $6

500K

1928

GPT-5.6 Sol (xHigh, Codex Harness)

OpenAI · Proprietary

1616+6/-6

17,605

$4 / $20

1.1M

2429

GLM-5.3-Flash

Z.ai · MIT

1605+7/-7

17,579

$0.05 / $0.18

2429

GLM-5.2 (Max)

Z.ai · MIT

1605+6/-6

16,407

$1.40 / $4.40

2734

Qwen3.8-27B

Alibaba · Apache 2.0

1593+7/-7

15,940

$0.40 / $3

N/A

2935

Gemini 3.7 Flash (High)

Google · Proprietary

1591+7/-7

12,258

$0.75 / $3.75

2935

Gemini 3.8 Flash (High)

Google · Proprietary

1585+7/-7

10,514

$0.75 / $3.75

2936

Claude Haiku 5.5 (High)

Anthropic · Proprietary

1585+11/-11

3,156

$0.10 / $0.50

2936

DeepSeek-V4-Pro (High, 20260813)

DeepSeek · MIT

1582+9/-9

4,728

$1.32 / $3.96

N/A

2936

DeepSeek-V4-Flash (High)

DeepSeek · MIT

1581+9/-9

4,963

$0.30 / $1.20

3036

GPT-6 Luna (Max)

OpenAI · Proprietary

1578+6/-6

20,045

$0.10 / $0.50

1.1M

3241

Step 5 Preview (High)

StepFun · Proprietary

1565+10/-10

4,424

$1 / $2.70

3642

Claude Opus 4.7 (High)

Anthropic · Proprietary

1558+6/-6

17,932

$5 / $25

3643

Claude Opus 4.7

Anthropic · Proprietary

1556+6/-6

18,244

$5 / $25

3643

Claude Opus 4.8 (High)

Anthropic · Proprietary

1556+6/-6

18,519

$5 / $25

3645

Grok 4.5

SpaceXAI · Proprietary

1553+7/-7

11,098

$2 / $6

500K

3748

Claude Opus 4.6 (High)

Anthropic · Proprietary

1547+5/-5

19,402

$5 / $25

3848

Muse Spark 1.1

Meta · Proprietary

1542+8/-8

7,990

$1.25 / $4.25

N/A

3649

Mistral Large 4

Mistral · Proprietary

1542+13/-13

2,536

$0.68 / $2.09

4048

Claude Sonnet 5 (High)

Anthropic · Proprietary

1541+6/-6

15,495

$2 / $10

4149

Gemini 3.6 Flash (High)

Google · Proprietary

1538+7/-7

8,758

$0.75 / $3.75

4148

Claude Opus 4.6

Anthropic · Proprietary

1537+5/-5

20,659

$5 / $25

4149

Claude Opus 4.8

Anthropic · Proprietary

1536+6/-6

17,426

$5 / $25

4054

Muse Spark 1.2 (xHigh)

Meta · Proprietary

1534+14/-14

2,162

$1.25 / $4.25

N/A

4856

Claude Sonnet 4.6

Anthropic · Proprietary

1523+5/-5

22,841

$1.50 / $7.50

4857

GPT-5.6 Terra (xHigh, Codex Harness)

OpenAI · Proprietary

1522+6/-6

13,678

$2 / $12

4858

Seed2.1 Pro Preview

Bytedance · Proprietary

1520+6/-6

14,893

$0.88 / $4.42

262.1K

4859

GPT-5.6 Luna (xHigh, Codex Harness)

OpenAI · Proprietary

1519+6/-6

12,646

$0.20 / $1.20

4859

Qwen3.7-Max (20260517)

Alibaba · Proprietary

1515+7/-7

8,892

$1.48 / $4.42

4960

GPT-5.5 (xHigh, Codex Harness)

OpenAI · Proprietary

1513+6/-6

15,655

$5 / $30

N/A

4564

Muse Spark Open (Max)

Meta · muse-model-license

1511+20/-20

991

$1.25 / $4.25

5060

Kimi K2.6

Moonshot · Modified MIT

1510+7/-7

10,166

$0.95 / $4

262.1K

5161

GLM-5.1

Z.ai · MIT

1508+7/-7

10,715

$1.40 / $4.40

202.8K

5262

Hy3

Tencent · Apache 2.0

1506+8/-8

6,168

$0.08 / $0.33

262.1K

4964

gemini-3.5-flash

Google · Proprietary

1504+15/-15

1,821

$0.75 / $4.50

5464

Gemini 3.5 Flash (High)

Google · Proprietary

1500+7/-7

9,400

$0.75 / $4.50

5666

Claude Opus 4.5 (High, 32K, 20251101)

Anthropic · Proprietary

1494+8/-8

11,030

$5 / $25

200K

5766

Gemini 3.5 Flash (Medium)

Google · Proprietary

1491+7/-7

12,158

$0.75 / $4.50

5869

GPT-5.5 (High, Codex Harness)

OpenAI · Proprietary

1487+6/-6

17,970

$5 / $30

N/A

5871

Qwen3.6-Max-Preview

Alibaba · Proprietary

1483+13/-13

2,711

$1.27 / $7.61

262.1K

6169

MiniMax-M3

MiniMax · MiniMax Community License

1482+6/-6

19,499

$0.30 / $1.20

524.3K

6170

MiMo-V2.5-Pro

Xiaomi · MIT

1481+5/-5

22,166

$0.43 / $0.87

1.1M

6372

Kimi K2.7 Code

Moonshot · Modified MIT

1474+9/-9

4,966

$0.67 / $3.35

262.1K

6572

Claude Opus 4.5 (20251101)

Anthropic · Proprietary

1469+7/-7

13,418

$5 / $25

200K

6674

DeepSeek-V4-Pro Preview (High)

DeepSeek · MIT

1464+6/-6

13,175

$1.32 / $3.96

6380

GPT-5.4 (High, Codex Harness)

OpenAI · Proprietary

1464+19/-19

1,349

$2.50 / $15

1.1M

6774

Qwen3.6-Plus

Alibaba · Proprietary

1462+6/-6

18,599

$0.33 / $1.95

6977

GPT-5.5 (Codex Harness)

OpenAI · Proprietary

1456+6/-6

15,887

$5 / $30

N/A

7184

DeepSeek-V4-Pro

DeepSeek · MIT

1447+6/-6

13,984

$1.32 / $3.96

7184

Gemini 3.1 Pro Preview

Google · Proprietary

1447+5/-5

24,223

$1 / $6

6987

GPT-5.4 (Medium, Codex Harness)

OpenAI · Proprietary

1444+18/-18

1,376

$2.50 / $15

1.1M

6399

Gemini 3.5 Flash-Lite

Google · Proprietary

1441+41/-41

241

$0.15 / $1.25

7287

Gemini 3 Pro

Google · Proprietary

1440+8/-8

14,092

$2 / $12

7287

Gemini 3 Flash

Google · Proprietary

1440+9/-9

10,890

$0.50 / $3

7387

MiMo-V2.5

Xiaomi · MIT

1438+6/-6

14,915

$0.14 / $0.28

1.1M

7187

beam-1.0-501b-a23b

Reflection · Apache 2.0

1438+13/-13

2,908

$1 / $3

7387

Kimi K2.5 (Thinking)

Moonshot · Modified MIT

1437+5/-5

20,099

$0.60 / $3

N/A

7387

GLM-5

Z.ai · MIT

1435+8/-8

7,496

$1 / $3.20

202.8K

7287

GLM-4.7

Z.ai · MIT

1435+12/-12

4,007

$0.60 / $2.20

204.8K

7387

MiMo-V2-Pro

Xiaomi · Proprietary

1434+8/-8

7,245

$1.10 / $3.30

7587

DeepSeek-V4-Flash Preview (High)

DeepSeek · MIT

1431+7/-7

10,114

$0.30 / $1.20

7597

GPT-5 (Medium)

OpenAI · Proprietary

1418+16/-16

3,092

$1.25 / $10

400K

75100

GPT-5.2

OpenAI · Proprietary

1417+23/-23

1,081

$0.88 / $7

400K

8593

Inkling

Thinky · Apache 2.0

1414+6/-6

15,505

$1 / $4.05

524.3K

8599

Inkling-Small

Thinky · Apache 2.0

1409+9/-9

5,339

$0.45 / $1.20

524.3K

85101

GPT-5.3-Codex (Codex Harness)

OpenAI · Proprietary

1407+14/-14

2,641

$1.75 / $14

400K

85101

Kimi K2.5 (Instant)

Moonshot · Modified MIT

1405+12/-12

3,264

$0.50 / $2.50

262.1K

85102

GPT-5.4

OpenAI · Proprietary

1402+10/-10

4,074

$2.50 / $15

1.1M

85103

GLM-5V-Turbo

Z.ai · Proprietary

1402+13/-13

2,405

$1.20 / $4

202.8K

8699

Qwen3.5-397B-A17B

Alibaba · Apache 2.0

1400+5/-5

21,161

$0.50 / $3.60

262.1K

86101

MiniMax-M2.7

MiniMax · Modified MIT

1399+6/-6

15,981

$0.30 / $1.20

204.8K

86102

GPT-5.4 mini (High)

OpenAI · Proprietary

1398+7/-7

11,944

$0.75 / $4.50

400K

86103

GPT-5.1 (Medium)

OpenAI · Proprietary

1396+12/-12

4,910

$0.63 / $5

400K

87103

Claude Sonnet 4.5 (High, 32K, 20250929)

Anthropic · Proprietary

1394+8/-8

13,251

$3 / $15

200K

87106

Claude Opus 4.1 (20250805)

Anthropic · Proprietary

1390+11/-11

6,927

$7.50 / $37.50

200K

100

90106

MiniMax-M2.5

MiniMax · Modified MIT

1386+8/-8

7,623

$0.27 / $0.95

204.8K

101

94106

Claude Sonnet 4.5 (20250929)

Anthropic · Proprietary

1385+7/-7

15,723

$3 / $15

102

96106

Gemini 3 Flash (Minimal)

Google · Proprietary

1385+5/-5

22,155

$0.50 / $3

103

91107

MiniMax-M2.1 Preview

MiniMax · MIT

1384+10/-10

7,639

$0.30 / $1.20

204.8K

104

99111

Grok 4.20 Beta (Reasoning, 0309)

SpaceXAI · Proprietary

1376+6/-6

15,455

$1.25 / $2.50

105

99114

GPT-5.3-Codex (Codex Harness)

OpenAI · Proprietary

1371+11/-11

3,656

$1.75 / $14

400K

106

99114

Solar Pro 4

Upstage · Proprietary

1371+10/-10

4,660

$0.09 / $0.36

524.3K

107

104114

Gemma 4 31B

Google · Apache 2.0

1367+6/-6

14,490

$0.99 / $1.49

131.1K

108

104115

DeepSeek-V3.2 (Thinking)

DeepSeek · MIT

1362+9/-9

6,915

$0.28 / $0.42

163.8K

109

105115

Qwen3.5-122B-A10B

Alibaba · Apache 2.0

1361+8/-8

8,241

$0.26 / $2.08

262.1K

110

103119

Gemma 4 26B A4B

Google · Apache 2.0

1359+17/-17

1,502

N/A

111

105116

Qwen3.5-27B

Alibaba · Apache 2.0

1358+8/-8

7,782

$0.26 / $2.60

262.1K

112

105116

Grok 4.3

SpaceXAI · Proprietary

1358+6/-6

14,966

$1.25 / $2.50

113

104120

Hy3 preview

Tencent · tencent-hunyuan-community

1357+17/-17

1,447

$0.18 / $0.60

262.1K

114

104120

Muse Glimmer

Meta · Apache-2.0

1355+16/-16

1,647

N/A

115

108119

Laguna M.1

Poolside · Apache 2.0

1350+9/-9

5,396

$0.20 / $0.40

262.1K

116

112122

GPT-5.1

OpenAI · Proprietary

1342+8/-8

10,711

$0.63 / $5

400K

117

110122

GLM-4.6

Z.ai · MIT

1341+11/-11

6,781

$0.50 / $2

204.8K

118

112122

GPT-5.2-Codex

OpenAI · Proprietary

1339+9/-9

6,720

$1.75 / $14

400K

119

112123

GPT-5.1-Codex

OpenAI · Proprietary

1337+12/-12

5,007

$1.25 / $10

400K

120

114123

MiMo-V2-Flash (Non-Thinking)

Xiaomi · MIT

1330+10/-10

5,689

$0.10 / $0.30

262.1K

121

116123

Claude Haiku 4.5 (20251001)

Anthropic · Proprietary

1330+5/-5

29,088

$1 / $5

200K

122

116123

DeepSeek-V3.2

DeepSeek · MIT

1326+8/-8

9,382

$0.28 / $0.42

163.8K

123

119123

Kimi K2 Thinking Turbo

Moonshot · Modified MIT

1322+7/-7

13,093

$0.57 / $2.30

131.1K

124

124126

Laguna XS.2

Poolside · Apache 2.0

1302+11/-11

4,231

$0.10 / $0.20

262.1K

125

124126

MiniMax-M2

MiniMax · Apache 2.0

1297+11/-11

6,713

$0.30 / $1.20

204.8K

126

124129

MiMo-V2-Flash (Thinking)

Xiaomi · MIT

1293+16/-16

1,686

$0.10 / $0.30

262.1K

127

126131

Qwen3-Coder-480B-A35B-Instruct

Alibaba · Apache 2.0

1275+8/-8

12,712

$0.65 / $3.25

128

126134

DeepSeek-V3.2-Exp

DeepSeek · MIT

1272+14/-14

3,969

$0.27 / $0.41

163.8K

129

126137

Mistral Medium 3.5

Mistral · Modified MIT

1264+15/-15

2,320

$0.75 / $3.75

262.1K

130

128137

Gemini 3.1 Flash-Lite Preview

Google · Proprietary

1257+7/-7

14,389

$0.25 / $1.50

131

127139

KAT-Coder-Pro V1

Proprietary

1256+19/-19

1,504

$0.21 / $0.83

256K

132

127139

Qwen3.5-35B-A3B

Alibaba · Apache 2.0

1254+17/-17

1,617

$0.15 / $1

262.1K

133

128139

Qwen3.5-Flash

Alibaba · Proprietary

1244+20/-20

1,329

N/A

134

128139

GPT-5.1-Codex-Mini

OpenAI · Proprietary

1244+22/-22

1,154

$0.25 / $2

400K

135

129139

Grok 4.1 Fast (Reasoning)

SpaceXAI · Proprietary

1242+11/-11

5,489

$0.20 / $0.50

128K

136

129139

Trinity Large Thinking

Apache 2.0

1238+20/-20

1,361

$0.25 / $0.80

262.1K

137

129141

Mistral Large 3

Mistral · Apache 2.0

1230+25/-25

839

$0.50 / $1.50

N/A

138

131141

Gemini 2.5 Pro

Google · Proprietary

1226+16/-16

2,730

$1.25 / $10

139

131143

Grok 4.1 (Thinking)

SpaceXAI · Proprietary

1215+25/-25

961

N/A

140

137144

Devstral 2

Mistral · Modified MIT

1197+21/-21

1,182

N/A

141

137144

Granite 4.1 8B

IBM · Apache 2.0

1193+18/-18

1,772

$0.05 / $0.10

131.1K

142

139144

Mercury 2

Inception AI · Proprietary

1171+24/-24

955

$0.25 / $0.75

128K

143

139144

Grok Code Fast 1

SpaceXAI · Proprietary

1166+28/-28

789

$0.20 / $1.50

N/A

144

140144

Grok 4 Fast (Reasoning)

SpaceXAI · Proprietary

1159+27/-27

742

$0.20 / $0.50

N/A

145

145145

Devstral Medium (2507)

Mistral · Proprietary

1071+31/-31

842

$0.40 / $2

128K

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.

Remove Style Control Leaderboard Plots

Domain

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.

Remove Style Control Leaderboard Plots

Fraction of Model A Wins in A vs. B Battles (Ties Excluded)

Average Win Rate Against Each Opponent (Ties Excluded)

Battle Count for Each Pair of Models (Ties Excluded)

Confidence Intervals on Model Strength (via Bootstrapping)