1
A
claude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
100.0
2.1K
1M
¥36 / ¥180Input/Output
Code · Image-to-WebDev · Image-to-WebDev Leaderboard
Ranking for Image-to-WebDev / Image-to-WebDev, based on public preference data.
Image-to-WebDev model ranking guide
Ranking for Image-to-WebDev / Image-to-WebDev, based on public preference data.
claude-opus-4-7-thinkingclaude-sonnet-4-6claude-opus-4-7claude-opus-4-6-thinkinggpt-5.5-xhigh (codex-harness)
2
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
95.5
3.2K
1M
¥21.6 / ¥108Input/Output
3
Aclaude-opus-4-7
claude-opus-4-7Anthropic
90.9
2.4K
1M
¥36 / ¥180Input/Output
4
Aclaude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
86.4
3K
1M
¥36 / ¥180Input/Output
5
O
gpt-5.5-xhigh (codex-harness)
gpt-5.5-xhigh (codex-harness)Openai
81.8
1.8K
400K
¥9 / ¥72Input/Output
6
Aclaude-opus-4-6
claude-opus-4-6Anthropic
77.3
3K
1M
¥36 / ¥180Input/Output
7
M
kimi-k2.6
kimi-k2.6Moonshot
72.7
1.5K
262K
¥6.84 / ¥28.8Input/Output
8
Ogpt-5.5-high (codex-harness)
gpt-5.5-high (codex-harness)Openai
68.2
2K
400K
¥9 / ¥72Input/Output
9
G
gemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
63.6
3.6K
1.05M
¥14.4 / ¥86.4Input/Output
10
Ogpt-5.5 (codex-harness)
gpt-5.5 (codex-harness)Openai
59.1
1.9K
400K
¥9 / ¥72Input/Output
11
A
qwen3.6-plus
qwen3.6-plusAlibaba
54.5
2.6K
1M
¥3.6 / ¥21.6Input/Output
12
Ggemini-3-pro
gemini-3-proGoogle
50.0
1.1K
1.05M
¥14.4 / ¥86.4Input/Output
13
Ggemini-3-flash
gemini-3-flashGoogle
45.5
4.4K
1.05M
¥3.6 / ¥21.6Input/Output
14
Ogpt-5.3-codex (codex-harness)
gpt-5.3-codex (codex-harness)Openai
40.9
2.5K
400K
¥9 / ¥72Input/Output
15
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
36.4
1.7K
262K
¥4.32 / ¥21.6Input/Output
16
Ogpt-5.4
gpt-5.4Openai
31.8
1.2K
1.05M
¥18 / ¥108Input/Output
17
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
27.3
4.4K
1.05M
¥3.6 / ¥21.6Input/Output
18
Ogpt-5.1-high
gpt-5.1-highOpenai
22.7
1.1K
400K
¥9 / ¥72Input/Output
19
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
18.2
1.1K
262K
¥4.32 / ¥21.6Input/Output
20
X
grok-4.3
grok-4.3Xai
13.6
965
1M
¥9 / ¥18Input/Output
21
Ogpt-5.1
gpt-5.1Openai
9.1
1.3K
400K
¥9 / ¥72Input/Output
22
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
4.5
3.7K
1.05M
¥1.8 / ¥10.8Input/Output
23
Ggemini-2.5-pro
gemini-2.5-proGoogle
0.0
1.2K
1.05M
¥9 / ¥72Input/Output
claude-opus-4-7-thinking why it ranks first
claude-opus-4-7-thinking ranks first with a percent score of 100.0 and 2.1K samples. Use it as the first option for this leaderboard, then compare price, context and availability.
Do not only look at rank #1
Start with the leaderboard closest to your task. Compare the top models by score and sample size, then check price, context length, open or closed access, and provider availability.
Compare adjacent capabilities
FAQ
图片转网页排行榜看什么指标？
主要看排名、百分制分数、样本量和来源。分数用于快速比较同一榜单内模型表现，样本量用于判断结果稳定性。
为什么不同榜单不能直接混合成总分？
不同榜单的任务、样本和评测口径不同，模力榜默认只在同一榜单内排序，避免把写作、代码、图像等能力强行合并。
图片转网页模型应该怎么选？
优先看与你任务最接近的榜单，再结合价格、上下文长度、开源闭源和厂商可用性。排名靠前不代表适合所有预算和部署方式。
榜单多久更新？
页面展示的是最新成功采集的公开榜单数据。当前优先使用 LMArena leaderboard dataset，并在页面来源中保留原始链接。