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.

Jul 17, 2026

69,997 votes

31 models

Rank by

	Rank Spread
1	11	claude-fable-5 Anthropic · Proprietary	1627+15/-15	1,930	$10 / $50	1M
2	23	claude-opus-4-7-thinking Anthropic · Proprietary	1581+12/-12	4,282	$5 / $25	1M
3	24	claude-opus-4-7 Anthropic · Proprietary	1567+11/-11	4,618	$5 / $25	1M
4	310	claude-opus-4-6-thinking Anthropic · Proprietary	1547+11/-11	5,279	$5 / $25	1M
5	410	claude-sonnet-4-6 Anthropic · Proprietary	1544+11/-11	5,538	$3 / $15	1M
6	411	claude-opus-4-6 Anthropic · Proprietary	1537+11/-11	5,273	$5 / $25	1M
7	412	claude-sonnet-5-high Anthropic · Proprietary	1533+16/-16	1,492	$2 / $10	1M
8	412	gpt-5.5-xhigh (codex-harness) OpenAI · Proprietary	1525+11/-11	4,210	$5 / $30	N/A
9	613	kimi-k2.6 Moonshot · Modified MIT	1519+12/-12	3,287	$0.95 / $4	262.1K
10	415	seed-2.1-pro-preview Bytedance · Proprietary	1518+22/-22	739	N/A	N/A
11	415	kimi-k2.7-code Moonshot · Modified MIT	1517+21/-21	822	$0.82 / $3.75	262.1K
12	714	gpt-5.5-high (codex-harness) OpenAI · Proprietary	1510+11/-11	4,607	N/A	N/A
13	1017	gpt-5.5 (codex-harness) OpenAI · Proprietary	1495+11/-11	4,344	N/A	N/A
14	918	gemini-3.5-flash-medium Google · Proprietary	1487+19/-19	984	$1.50 / $9	1M
15	1318	gemini-3.1-pro-preview Google · Proprietary	1482+10/-10	5,891	$2 / $12	1M
16	1119	minimax-m3 MiniMax · MiniMax Community License	1481+16/-16	1,422	$0.60 / $2.40	N/A
17	1319	qwen3.6-plus Alibaba · Proprietary	1473+11/-11	4,887	$0.33 / $1.95	1M
18	1622	gemini-3-flash Google · Proprietary	1457+9/-9	6,893	$0.50 / $3	1M
19	1426	gemini-3-pro Google · Proprietary	1453+21/-21	1,091	$2 / $12	1M
20	1826	gpt-5.3-codex (codex-harness) OpenAI · Proprietary	1440+14/-14	2,498	$1.75 / $14	400K
21	1826	kimi-k2.5-thinking Moonshot · Modified MIT	1439+17/-17	1,736	$0.60 / $3	N/A
22	1826	gpt-5.4 OpenAI · Proprietary	1435+16/-16	1,624	$2.50 / $15	1.1M
23	1926	gemini-3-flash (thinking-minimal) Google · Proprietary	1426+10/-10	6,692	$0.50 / $3	1M
24	1926	gpt-5.1-high OpenAI · Proprietary	1421+21/-21	1,112	$1.25 / $10	400K
25	1926	glm-5v-turbo Z.ai · Proprietary	1420+18/-18	1,214	$1.20 / $4	202.8K
26	1926	kimi-k2.5-instant Moonshot · Modified MIT	1415+21/-21	1,094	$0.57 / $2.85	262.1K
27	2728	grok-4.3 SpaceXAI · Proprietary	1371+12/-12	3,327	$1.25 / $2.50	1M
28	2730	gpt-5.1 OpenAI · Proprietary	1345+20/-20	1,262	$1.25 / $10	400K
29	2830	gemini-3.1-flash-lite-preview Google · Proprietary	1330+11/-11	5,818	$0.25 / $1.50	1M
30	2831	mistral-large-3 Mistral · Apache 2.0	1307+42/-42	266	$0.50 / $1.50	N/A
31	3031	gemini-2.5-pro Google · Proprietary	1276+20/-20	1,181	$1.25 / $10	1M

Remove Style Control Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Fraction of Model A Wins for All Non-tied A vs. B Battles

Battle Count for Each Combination of Models (without Ties)

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

Rank Spread

claude-fable-5

Anthropic · Proprietary

1627+15/-15

1,930

$10 / $50

claude-opus-4-7-thinking

Anthropic · Proprietary

1581+12/-12

4,282

$5 / $25

claude-opus-4-7

Anthropic · Proprietary

1567+11/-11

4,618

$5 / $25

310

claude-opus-4-6-thinking

Anthropic · Proprietary

1547+11/-11

5,279

$5 / $25

410

claude-sonnet-4-6

Anthropic · Proprietary

1544+11/-11

5,538

$3 / $15

411

claude-opus-4-6

Anthropic · Proprietary

1537+11/-11

5,273

$5 / $25

412

claude-sonnet-5-high

Anthropic · Proprietary

1533+16/-16

1,492

$2 / $10

412

gpt-5.5-xhigh (codex-harness)

OpenAI · Proprietary

1525+11/-11

4,210

$5 / $30

N/A

613

kimi-k2.6

Moonshot · Modified MIT

1519+12/-12

3,287

$0.95 / $4

262.1K

415

seed-2.1-pro-preview

Bytedance · Proprietary

1518+22/-22

739

N/A

415

kimi-k2.7-code

Moonshot · Modified MIT

1517+21/-21

822

$0.82 / $3.75

262.1K

714

gpt-5.5-high (codex-harness)

OpenAI · Proprietary

1510+11/-11

4,607

N/A

1017

gpt-5.5 (codex-harness)

OpenAI · Proprietary

1495+11/-11

4,344

N/A

918

gemini-3.5-flash-medium

Google · Proprietary

1487+19/-19

984

$1.50 / $9

1318

gemini-3.1-pro-preview

Google · Proprietary

1482+10/-10

5,891

$2 / $12

1119

minimax-m3

MiniMax · MiniMax Community License

1481+16/-16

1,422

$0.60 / $2.40

N/A

1319

qwen3.6-plus

Alibaba · Proprietary

1473+11/-11

4,887

$0.33 / $1.95

1622

gemini-3-flash

Google · Proprietary

1457+9/-9

6,893

$0.50 / $3

1426

gemini-3-pro

Google · Proprietary

1453+21/-21

1,091

$2 / $12

1826

gpt-5.3-codex (codex-harness)

OpenAI · Proprietary

1440+14/-14

2,498

$1.75 / $14

400K

1826

kimi-k2.5-thinking

Moonshot · Modified MIT

1439+17/-17

1,736

$0.60 / $3

N/A

1826

gpt-5.4

OpenAI · Proprietary

1435+16/-16

1,624

$2.50 / $15

1.1M

1926

gemini-3-flash (thinking-minimal)

Google · Proprietary

1426+10/-10

6,692

$0.50 / $3

1926

gpt-5.1-high

OpenAI · Proprietary

1421+21/-21

1,112

$1.25 / $10

400K

1926

glm-5v-turbo

Z.ai · Proprietary

1420+18/-18

1,214

$1.20 / $4

202.8K

1926

kimi-k2.5-instant

Moonshot · Modified MIT

1415+21/-21

1,094

$0.57 / $2.85

262.1K

2728

grok-4.3

SpaceXAI · Proprietary

1371+12/-12

3,327

$1.25 / $2.50

2730

gpt-5.1

OpenAI · Proprietary

1345+20/-20

1,262

$1.25 / $10

400K

2830

gemini-3.1-flash-lite-preview

Google · Proprietary

1330+11/-11

5,818

$0.25 / $1.50

2831

mistral-large-3

Mistral · Apache 2.0

1307+42/-42

266

$0.50 / $1.50

N/A

3031

gemini-2.5-pro

Google · Proprietary

1276+20/-20

1,181

$1.25 / $10