Code Arena | Image-to-WebDev

View overall rankings across AI models on their ability to generate websites from images and screenshots, alongside agentic coding workflows that involve multi-step reasoning and tool use.

Oct 9, 2026

177,108 votes

64 models

	Rank Spread
1	15	claude-opus-5.5-max Anthropic · Proprietary	1749+30/-30	493	$4 / $20	1M
2	15	claude-sonnet-5.5-xhigh Anthropic · Proprietary	1740+20/-20	1,074	$2 / $10	1M
3	15	gpt-6-astra-max OpenAI · Proprietary	1731+13/-13	2,739	$10 / $50	1.1M
4	15	claude-fable-5.1-max Anthropic · Proprietary	1720+14/-14	2,470	$10 / $50	1M
5	15	gpt-6.1-sol-max OpenAI · Proprietary	1703+17/-17	1,430	$2 / $10	1.1M
6	69	gpt-6-sol-max OpenAI · Proprietary	1661+13/-13	2,426	$2 / $10	1.1M
7	69	claude-opus-5-max Anthropic · Proprietary	1661+10/-10	4,250	$5 / $25	1M
8	69	muse-spark-1.3-max Meta · Proprietary	1642+10/-10	4,688	$1.25 / $4.25	1M
9	612	qwen3.8-max-0902 Alibaba · Proprietary	1638+18/-18	1,164	$2 / $6	1M
10	914	claude-fable-5-high Anthropic · Proprietary	1622+9/-9	5,457	$10 / $50	1M
11	919	qwen3.8-max Alibaba · Proprietary	1614+10/-10	3,971	$2 / $6	1M
12	923	deepseek-v4.1-flash-max DeepSeek · MIT	1609+22/-22	766	$0.30 / $1.20	1M
13	1020	gpt-5.6-sol-xhigh (codex-harness) OpenAI · Proprietary	1608+10/-10	4,478	$4 / $20	1.1M
14	1021	gemini-3.7-flash-high Google · Proprietary	1603+13/-13	2,144	$0.75 / $3.75	1M
15	1122	grok-4.6-high SpaceXAI · Proprietary	1601+12/-12	2,826	$2 / $6	500K
16	1124	muse-spark-1.3 (xHigh) Meta · Proprietary	1598+14/-14	2,152	$1.25 / $4.25	1M
17	1124	mimo-v2.6-flash Xiaomi · MIT	1597+14/-14	1,930	$0.14 / $0.28	1.1M
18	1125	mimo-v2.6-pro Xiaomi · MIT	1595+13/-13	2,199	$0.43 / $0.87	1.1M
19	1125	gemini-3.8-flash-high Google · Proprietary	1593+14/-14	2,015	$0.75 / $3.75	1M
20	1326	glm-5.3-flash Z.ai · MIT	1581+10/-10	4,315	$0.06 / $0.20	1M
21	1427	kimi-k3-max Moonshot · Kimi K3 license	1579+11/-11	3,504	$3 / $15	1M
22	1527	claude-opus-4-7-high Anthropic · Proprietary	1578+9/-9	6,942	$5 / $25	1M
23	1228	grok-4.7-xhigh SpaceXAI · Proprietary	1577+21/-21	796	$2 / $6	500K
24	1627	qwen3.8-27b Alibaba · Apache 2.0	1576+9/-9	5,117	$0.40 / $3	N/A
25	1828	gpt-6-luna-max OpenAI · Proprietary	1570+12/-12	3,000	$0.10 / $0.50	1.1M
26	2029	grok-4.5 SpaceXAI · Proprietary	1564+10/-10	3,909	$2 / $6	500K
27	2129	claude-opus-4-7 Anthropic · Proprietary	1562+9/-9	7,474	$5 / $25	1M
28	2439	gemini-3.6-flash-high Google · Proprietary	1545+14/-14	1,799	$0.75 / $3.75	1M
29	2837	claude-opus-4-6-high Anthropic · Proprietary	1543+9/-9	7,930	$5 / $25	1M
30	2641	step-5-preview-high StepFun · Proprietary	1541+15/-15	1,880	$1 / $2.70	1M
31	2839	gpt-5.6-terra-xhigh (codex-harness) OpenAI · Proprietary	1540+10/-10	4,331	$2 / $12	1M
32	2839	muse-spark-1.1 Meta · Proprietary	1540+11/-11	3,118	$1.25 / $4.25	1M
33	2839	claude-sonnet-5-high Anthropic · Proprietary	1539+8/-8	7,633	$2 / $10	1M
34	2839	claude-opus-4-6 Anthropic · Proprietary	1539+9/-9	8,068	$5 / $25	1M
35	2841	gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary	1532+9/-9	6,794	$5 / $30	N/A
36	2841	claude-sonnet-4-6 Anthropic · Proprietary	1529+9/-9	8,306	$1.50 / $7.50	1M
37	2945	kimi-k2.6 Moonshot · Modified MIT	1521+11/-11	3,593	$0.95 / $4	262.1K
38	3445	gpt-5.5-high (codex-harness) OpenAI · Proprietary	1519+9/-9	7,427	$5 / $30	1.1M
39	3445	gpt-5.6-luna-xhigh (codex-harness) OpenAI · Proprietary	1517+10/-10	4,303	$0.20 / $1.20	1M
40	2945	kimi-k2.7-code Moonshot · Modified MIT	1513+20/-20	921	$0.67 / $3.35	262.1K
41	2848	gemini-3.5-flash Google · Proprietary	1512+31/-31	414	$0.75 / $4.50	1M
42	3745	seed-2.1-pro-preview Bytedance · Proprietary	1510+10/-10	3,600	$0.88 / $4.42	262.1K
43	3745	gemini-3.5-flash-medium Google · Proprietary	1505+12/-12	2,865	$0.75 / $4.50	1M
44	3745	gpt-5.5 (codex-harness) OpenAI · Proprietary	1503+9/-9	7,048	$5 / $30	1.1M
45	3746	gemini-3.5-flash-high Google · Proprietary	1501+14/-14	2,020	$0.75 / $4.50	1M
46	4448	gemini-3.1-pro-preview Google · Proprietary	1481+9/-9	8,212	$1 / $6	1M
47	4548	minimax-m3 MiniMax · MiniMax Community License	1473+9/-9	5,514	$0.30 / $1.20	524.3K
48	4550	qwen3.6-plus Alibaba · Proprietary	1472+10/-10	5,844	$0.33 / $1.95	1M
49	4955	gemini-3-flash Google · Proprietary	1451+9/-9	7,654	$0.50 / $3	1M
50	4858	gemini-3.5-flash-lite Google · Proprietary	1447+15/-15	1,600	$0.15 / $1.25	1M
51	4958	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1444+14/-14	2,670	$1.75 / $14	400K
52	4859	gemini-3-pro Google · Proprietary	1441+22/-22	964	$2 / $12	1M
53	4959	gpt-5.4 OpenAI · Proprietary	1440+12/-12	3,076	$2.50 / $15	1.1M
54	4959	kimi-k2.5-thinking Moonshot · Modified MIT	1440+17/-17	1,652	$0.60 / $3	N/A
55	5059	gemini-3-flash (thinking-minimal) Google · Proprietary	1431+9/-9	7,521	$0.50 / $3	1M
56	5059	glm-5v-turbo Z.ai · Proprietary	1425+16/-16	1,560	$1.20 / $4	202.8K
57	4959	gpt-5.1-high OpenAI · Proprietary	1421+22/-22	999	$0.63 / $5	400K
58	5059	kimi-k2.5-instant Moonshot · Modified MIT	1411+22/-22	969	$0.50 / $2.50	262.1K
59	5259	Inkling Small Thinky · Apache 2.0	1410+19/-19	1,024	$0.45 / $1.20	524.3K
60	6062	grok-4.3 SpaceXAI · Proprietary	1375+10/-10	5,864	$1.25 / $2.50	1M
61	6063	mistral-large-3 Mistral · Apache 2.0	1362+17/-17	1,413	$0.50 / $1.50	N/A
62	6063	gpt-5.1 OpenAI · Proprietary	1351+21/-21	1,123	$0.63 / $5	400K
63	6163	gemini-3.1-flash-lite-preview Google · Proprietary	1337+11/-11	6,518	$0.25 / $1.50	1M
64	6464	gemini-2.5-pro Google · Proprietary	1285+21/-21	1,049	$1.25 / $10	1M

Code Arena | Image-to-WebDev

View overall rankings across AI models on their ability to generate websites from images and screenshots, alongside agentic coding workflows that involve multi-step reasoning and tool use.

Remove Style Control Leaderboard Plots

Code Arena | Image-to-WebDev

View overall rankings across AI models on their ability to generate websites from images and screenshots, alongside agentic coding workflows that involve multi-step reasoning and tool use.

Remove Style Control Leaderboard Plots

Code Arena | Image-to-WebDev

View overall rankings across AI models on their ability to generate websites from images and screenshots, alongside agentic coding workflows that involve 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)

Code Arena | Image-to-WebDev

View overall rankings across AI models on their ability to generate websites from images and screenshots, alongside agentic coding workflows that involve 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)