> For the complete documentation index, see [llms.txt](https://docs.cherryai.com.cn/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.cherryai.com.cn/docs/en-us/other/model_rank/code-webdev.md).
# Code / Web Development Ranking
This page shows [Arena AI](https://arena.ai/leaderboard/code/webdev) Daily snapshot of the top 30 on the leaderboard, for a quick view of recent model performance. For the full leaderboard, filters, and latest changes, see the official Arena AI website.
This leaderboard evaluates models' real-world performance on Web frontend development (HTML/CSS/JS) tasks.
> **Data update time**: 2026-09-20 12:49:40 UTC / 2026-09-20 20:49:40 CST (Beijing time)
{% hint style="info" %}
The leaderboard reflects specific evaluations and user voting preferences, and does not necessarily mean the model will be better for your task. When choosing a model, also consider price, speed, context, tool calling, privacy, and regional availability.
{% endhint %}
## Top 30
| Ranking | Rank range | Model | Score | Votes | Price $/million tokens | Context |
| ------: | ---------- | -------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------- | -----: | ---------------------- | ------- |
| 1 | 1-1 | gpt-6-astra-max [1](https://openai.com/index/gpt-6-astra/) | 1800 (++16/-16) | 2,281 | $10 / $50 | 1.1M |
| 2 | 2-2 | claude-fable-5.1-max [1](https://www.anthropic.com/claude-fable-and-mythos-5-1) | 1758 (++14/-14) | 3,036 | $10 / $50 | 1M |
| 3 | 3-6 | claude-opus-5-max [1](https://www.anthropic.com/news/claude-opus-5) | 1687 (++7/-7) | 12,087 | $5 / $25 | 1M |
| 4 | 3-7 | qwen3.8-max-0902 [1](https://www.qianwenai.com/models/qwen3.8-max-0902) | 1681 (++15/-15) Preliminary | 2,262 | $2 / $6 | N/A |
| 5 | 3-8 | kimi-k3-max [1](https://platform.kimi.ai/docs/guide/kimi-k3-quickstart) | 1674 (++11/-11) | 4,547 | $3 / $15 | 1M |
| 6 | 3-8 | qwen3.8-max [1](https://www.qwencloud.com/models/qwen3.8-max) | 1671 (++12/-12) Preliminary | 3,221 | $2 / $6 | 1M |
| 7 | 4-8 | claude-opus-5-high [1](https://www.anthropic.com/news/claude-opus-5) | 1660 (++7/-7) | 12,566 | $5 / $25 | 1M |
| 8 | 5-9 | muse-spark-1.3-max [1](https://developer.meta.com/ai/models/muse-spark/) | 1652 (++12/-12) | 2,972 | $1.25 / $4.25 | 1M |
| 9 | 8-16 | qwen3.8-flash-next [1](https://qwen.ai/blog?id=qwen3.8-flash-next) | 1635 (++13/-13) Preliminary | 2,779 | $0.16 / $0.47 | 1M |
| 10 | 9-16 | claude-fable-5-high [1](https://www.anthropic.com/news/claude-fable-5-mythos-5) | 1628 (++7/-7) | 10,081 | $10 / $50 | 1M |
| 11 | 9-17 | hy4-preview [1](https://hy.tencent.ai/research/hy4-preview) | 1624 (++13/-13) Preliminary | 2,321 | $0.83 / $2.50 | 1M |
| 12 | 9-17 | muse-spark-1.3 (xHigh) [1](https://developer.meta.com/ai/models/muse-spark/) | 1623 (++14/-14) | 2,123 | $1.25 / $4.25 | 1M |
| 13 | 9-17 | grok-4.6-high [1](https://docs.x.ai/developers/models/grok-4.6) | 1618 (++10/-10) | 4,282 | $2 / $6 | 500K |
| 14 | 9-17 | gpt-5.6-sol-xhigh (codex-harness) [1](https://openai.com/index/gpt-5-6/) | 1617 (++7/-7) | 11,916 | $4 / $20 | 1.1M |
| 15 | 9-17 | glm-5.3-max [1](https://z.ai/blog/glm-5.3) | 1614 (++11/-11) | 3,725 | $1.40 / $4.40 | 1M |
| 16 | 9-20 | deepseek-v4.1-flash-max [1](https://www.deepseek.com/en/news/deepseek-v4-1-flash/) | 1614 (++17/-17) | 1,361 | $0.30 / $1.20 | 1M |
| 17 | 11-20 | glm-5.3-flash [1](https://z.ai/blog/glm-5.3) | 1607 (++12/-12) | 2,925 | $0.07 / $0.25 | 1M |
| 18 | 16-22 | qwen3.8-27b [1](https://huggingface.co/Qwen/Qwen3.8-27B) | 1593 (++9/-9) | 4,913 | $0.40 / $3 | N/A |
| 19 | 16-22 | glm-5.2-max [1](https://huggingface.co/zai-org/GLM-5.2) | 1592 (++7/-7) | 10,516 | $1.40 / $4.40 | 1M |
| 20 | 16-23 | gemini-3.7-flash-high [1](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/) | 1587 (++12/-12) Preliminary | 3,007 | $0.75 / $3.75 | 1M |
| 21 | 18-23 | deepseek-v4-pro-high-20260813 [1](https://api-docs.deepseek.com/updates/#date-2026-08-13) | 1581 (++10/-10) | 4,258 | $1.32 / $3.96 | N/A |
| 22 | 18-23 | deepseek-v4-flash-high [1](https://api-docs.deepseek.com/updates/#date-2026-07-31) | 1580 (++10/-10) | 4,723 | $0.30 / $1.20 | 1M |
| 23 | 20-27 | gemini-3.8-flash-high [1](https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/) | 1568 (++12/-12) Preliminary | 2,732 | $0.75 / $3.75 | 1M |
| 24 | 23-27 | claude-opus-4-8-high [1](https://www.anthropic.com/news/claude-opus-4-8) | 1559 (++7/-7) | 13,787 | $5 / $25 | 1M |
| 25 | 23-28 | claude-opus-4-7 [1](https://www.anthropic.com/news/claude-opus-4-7) | 1557 (++6/-6) | 15,914 | $5 / $25 | 1M |
| 26 | 23-29 | claude-opus-4-7-high [1](https://www.anthropic.com/news/claude-opus-4-7) | 1555 (++6/-6) | 16,387 | $5 / $25 | 1M |
| 27 | 23-30 | grok-4.5 [1](https://docs.x.ai/developers/models/grok-4.5) | 1555 (++8/-8) | 8,133 | $2 / $6 | 500K |
| 28 | 25-34 | claude-opus-4-6-high [1](https://www.anthropic.com/news/claude-opus-4-6) | 1547 (++6/-6) | 18,332 | $5 / $25 | 1M |
| 29 | 26-34 | muse-spark-1.1 [1](https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/) | 1542 (++8/-8) | 7,549 | $1.25 / $4.25 | N/A |
| 30 | 28-34 | claude-opus-4-8 [1](https://www.anthropic.com/news/claude-opus-4-8) | 1539 (++6/-6) | 12,654 | $5 / $25 | 1M |
## How to read this table
* **Ranking / Rank range**：Relative ranking estimated by Arena AI based on head-to-head votes; rank range indicates rank fluctuations within the confidence interval.
* **Score**：Relative score, suitable for comparing models on the leaderboard at the same point in time.
* **Votes / Sessions**：Sample size reference; with fewer samples, rankings are usually more volatile.
* **Price $/million tokens**：Reference price per million input / output tokens.
* **Context**：Maximum context length supported by the model.
## Three things to confirm again when choosing a model
1. Whether the provider actually offers this model, and whether it is available in your region and account;
2. Whether the API price, rate limits, and context fit your task;
3. Run a small test with 3–5 real tasks; do not judge only by the overall leaderboard rank.
## Data source
Data comes from [Arena AI official code / Web development leaderboard](https://arena.ai/leaderboard/code/webdev)，updated daily by GitHub Actions. For model pricing, licenses, and capabilities, refer to the official information from the model provider.
---
# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.
## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://docs.cherryai.com.cn/docs/en-us/other/model_rank/code-webdev.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.