Best LLM for web development
- models ranked
- 101
- lead over #2
- +34 Elo
WebDev Arena Elo · read October 20
As of October 20, 2026, Anthropic Claude Opus 5.5 leads WebDev Arena with a rating of 1807, ahead of OpenAI GPT-6 Astra (1774) and Anthropic Claude Sonnet 5.5 (1768).
This list narrows the best LLM for coding ranking.
| Rank | Model | WebDev Arena Elo | Evidence | Coding index | Output $/Mtok |
|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 Anthropic | 1807 | 92.2 | $20.00 | |
| 2 | GPT-6 Astra OpenAI | 1774 | 88.7 | $50.00 | |
| 3 | Claude Sonnet 5.5 Anthropic | 1768 | 88.9 | $10.00 | |
| 4 | GPT-6.1 Sol OpenAI | 1753 | 88.7 | $10.00 | |
| 5 | Claude Fable 5.1 Anthropic | 1743 | 89.1 | $50.00 | |
| 6 | Claude Opus 5 Anthropic | 1689 | 81.8 | $25.00 | |
| 7 | GPT-6 Sol OpenAI | 1683 | 82.8 | $10.00 | |
| 8 | Gemini 4 Argon Google | 1678 | 80.5 | $10.00 | |
| 9 | Qwen3.8 Max (0902) Qwen | 1674 | 63.5 | $6.00 | |
| 10 | DeepSeek V4.1 Flash 1017 DeepSeek | 1664 | 83.3 | $0.60 | |
| 11 | Muse Spark 1.3 Meta | 1659 | 79.7 | $4.25 | |
| 12 | Kimi K3 Moonshot AI | 1655 | 61.8 | $11.936 | |
| 13 | Muse Wonder Meta | 1652 | 64.5 | $20.00 | |
| 14 | Grok 4.7 xAI | 1637 | 75.0 | $6.00 | |
| 15 | MiMo-V2.6-Flash Xiaomi | 1634 | 61.9 | $0.28 | |
| 16 | Hy4 preview Tencent | 1631 | 61.6 | $2.501 | |
| 17 | MiMo-V2.6-Pro Xiaomi | 1625 | 72.6 | $0.87 | |
| 18 | Claude Fable 5 Anthropic | 1624 | 82.1 | $50.00 | |
| 19 | GLM 5.3 Z.ai | 1621 | 73.1 | $1.40 | |
| 20 | DeepSeek V4.1 Flash DeepSeek | 1618 | 77.2 | $0.0112 |
How this list is built
Generated from the dataset on every refresh. Nobody picks the order by hand.
Models by their WebDev Arena rating, where people compare two models building the same web page and vote for the better one. Higher is better.
- LMArena WebDev, fetched