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 19, 2026

191,568 votes

65 models

	Rank Spread
1	14	Claude Opus 5.5 (Max) Anthropic · Proprietary	1753+24/-24	781	$4 / $20	1M
2	14	Claude Sonnet 5.5 (xHigh) Anthropic · Proprietary	1737+17/-17	1,551	$2 / $10	1M
3	15	GPT-6 Astra (Max) OpenAI · Proprietary	1726+12/-12	3,181	$10 / $50	1.1M
4	15	Claude Fable 5.1 (Max) Anthropic · Proprietary	1722+13/-13	2,907	$10 / $50	1M
5	35	GPT-6.1 Sol (Max) OpenAI · Proprietary	1702+15/-15	1,916	$2 / $10	1.1M
6	68	Claude Opus 5 (Max) Anthropic · Proprietary	1662+10/-10	4,671	$5 / $25	1M
7	69	GPT-6 Sol (Max) OpenAI · Proprietary	1660+12/-12	2,948	$2 / $10	1.1M
8	710	Muse Spark 1.3 (Max) Meta · Proprietary	1640+9/-9	5,679	$1.25 / $4.25	1M
9	613	Qwen3.8-Max (0902) Alibaba · Proprietary	1637+18/-18	1,163	$2 / $6	1M
10	814	Claude Fable 5 (High) Anthropic · Proprietary	1623+9/-9	5,855	$10 / $50	1M
11	919	Qwen3.8-Max Alibaba · Proprietary	1614+10/-10	4,203	$2 / $6	1M
12	920	GPT-5.6 Sol (xHigh, Codex Harness) OpenAI · Proprietary	1609+9/-9	4,969	$4 / $20	1.1M
13	924	DeepSeek-V4.1-Flash-20260910 (Max) DeepSeek · MIT	1606+22/-22	767	$0.30 / $1.20	1M
14	1020	Grok 4.6 (High) SpaceXAI · Proprietary	1603+11/-11	3,241	$2 / $6	500K
15	1122	Gemini 3.7 Flash (High) Google · Proprietary	1599+12/-12	2,661	$0.75 / $3.75	1M
16	1123	MiMo-V2.6-Pro Xiaomi · MIT	1598+12/-12	2,627	$0.43 / $0.87	1.1M
17	1124	Muse Spark 1.3 (xHigh) Meta · Proprietary	1596+12/-12	2,656	$1.25 / $4.25	1M
18	1124	MiMo-V2.6-Flash Xiaomi · MIT	1596+13/-13	2,318	$0.14 / $0.28	1.1M
19	1125	Gemini 3.8 Flash (High) Google · Proprietary	1593+13/-13	2,516	$0.75 / $3.75	1M
20	1227	Grok 4.7 (xHigh) SpaceXAI · Proprietary	1586+17/-17	1,191	$2 / $6	500K
21	1427	Kimi K3 (Max) Moonshot · Kimi K3 license	1579+10/-10	3,936	$3 / $15	1M
22	1427	GLM-5.3-Flash Z.ai · MIT	1578+9/-9	5,623	$0.05 / $0.18	1M
23	1527	Claude Opus 4.7 (High) Anthropic · Proprietary	1577+9/-9	6,946	$5 / $25	1M
24	1627	Qwen3.8-27B Alibaba · Apache 2.0	1577+8/-8	6,418	$0.40 / $3	N/A
25	1928	GPT-6 Luna (Max) OpenAI · Proprietary	1571+10/-10	4,439	$0.10 / $0.50	1.1M
26	2029	Claude Opus 4.7 Anthropic · Proprietary	1562+9/-9	7,474	$5 / $25	1M
27	2029	Grok 4.5 SpaceXAI · Proprietary	1562+10/-10	4,255	$2 / $6	500K
28	2535	Step 5 Preview (High) StepFun · Proprietary	1550+12/-12	3,300	$1 / $2.70	1M
29	2639	Gemini 3.6 Flash (High) Google · Proprietary	1545+14/-14	1,797	$0.75 / $3.75	1M
30	2836	Claude Opus 4.6 (High) Anthropic · Proprietary	1543+9/-9	7,938	$5 / $25	1M
31	2839	GPT-5.6 Terra (xHigh, Codex Harness) OpenAI · Proprietary	1541+9/-9	4,814	$2 / $12	1M
32	2838	Claude Sonnet 5 (High) Anthropic · Proprietary	1540+8/-8	8,124	$2 / $10	1M
33	2839	Muse Spark 1.1 Meta · Proprietary	1540+11/-11	3,120	$1.25 / $4.25	1M
34	2839	Claude Opus 4.6 Anthropic · Proprietary	1538+9/-9	8,074	$5 / $25	1M
35	2841	GPT-5.5 (xHigh, Codex Harness) OpenAI · Proprietary	1532+9/-9	6,795	$5 / $30	N/A
36	2941	Claude Sonnet 4.6 Anthropic · Proprietary	1529+9/-9	8,312	$1.50 / $7.50	1M
37	3045	Kimi K2.6 Moonshot · Modified MIT	1521+11/-11	3,591	$0.95 / $4	262.1K
38	3545	GPT-5.5 (High, Codex Harness) OpenAI · Proprietary	1519+9/-9	7,439	$5 / $30	1.1M
39	3545	GPT-5.6 Luna (xHigh, Codex Harness) OpenAI · Proprietary	1517+10/-10	4,324	$0.20 / $1.20	1M
40	3045	Kimi K2.7 Code Moonshot · Modified MIT	1513+20/-20	921	$0.67 / $3.35	262.1K
41	3745	Seed2.1 Pro Preview Bytedance · Proprietary	1510+10/-10	3,909	$0.88 / $4.42	262.1K
42	3147	gemini-3.5-flash Google · Proprietary	1506+26/-26	596	$0.75 / $4.50	1M
43	3745	Gemini 3.5 Flash (Medium) Google · Proprietary	1504+12/-12	2,865	$0.75 / $4.50	1M
44	3745	GPT-5.5 (Codex Harness) OpenAI · Proprietary	1503+9/-9	7,051	$5 / $30	1.1M
45	3746	Gemini 3.5 Flash (High) Google · Proprietary	1501+14/-14	2,024	$0.75 / $4.50	1M
46	4448	Gemini 3.1 Pro Preview Google · Proprietary	1481+9/-9	8,219	$1 / $6	1M
47	4550	Qwen3.6-Plus Alibaba · Proprietary	1472+10/-10	5,847	$0.50 / $3	1M
48	4650	MiniMax-M3 MiniMax · MiniMax Community License	1470+9/-9	5,983	$0.30 / $1.20	524.3K
49	4955	Gemini 3 Flash Google · Proprietary	1450+9/-9	7,660	$0.50 / $3	1M
50	4758	Gemini 3.5 Flash-Lite Google · Proprietary	1448+15/-15	1,603	$0.15 / $1.25	1M
51	4959	GPT-5.3-Codex (Codex Harness) OpenAI · Proprietary	1443+14/-14	2,671	$1.75 / $14	400K
52	4760	Gemini 3 Pro Google · Proprietary	1441+22/-22	964	$2 / $12	1M
53	4960	Kimi K2.5 (Thinking) Moonshot · Modified MIT	1439+17/-17	1,653	$0.60 / $3	N/A
54	4960	GPT-5.4 OpenAI · Proprietary	1436+12/-12	3,201	$2.50 / $15	1.1M
55	5060	Gemini 3 Flash (Minimal) Google · Proprietary	1431+9/-9	7,521	$0.50 / $3	1M
56	5060	GLM-5V-Turbo Z.ai · Proprietary	1425+16/-16	1,560	$1.20 / $4	202.8K
57	4960	GPT-5.1 (High) OpenAI · Proprietary	1421+22/-22	1,000	$0.63 / $5	400K
58	5060	Kimi K2.5 (Instant) Moonshot · Modified MIT	1411+22/-22	970	$0.50 / $2.50	262.1K
59	5160	Inkling-Small Thinky · Apache 2.0	1410+19/-19	1,025	$0.45 / $1.20	524.3K
60	5260	NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4) Nvidia · OpenMDW-1.1	1407+22/-22	991	N/A	N/A
61	6163	Grok 4.3 SpaceXAI · Proprietary	1375+10/-10	5,868	$1.25 / $2.50	1M
62	6164	Mistral Large 3 Mistral · Apache 2.0	1361+17/-17	1,410	$0.50 / $1.50	N/A
63	6164	GPT-5.1 OpenAI · Proprietary	1351+21/-21	1,123	$0.63 / $5	400K
64	6264	Gemini 3.1 Flash-Lite Preview Google · Proprietary	1336+11/-11	6,518	$0.25 / $1.50	1M
65	6565	Gemini 2.5 Pro Google · Proprietary	1285+21/-21	1,053	$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)