Code / Web Dev Leaderboard
This page shows the top 30 models on the Arena AI leaderboard, snapshotted daily so you can see how recent models are doing at a glance. See the Arena AI site for the full leaderboard, filters and latest changes.
This leaderboard measures how models perform in practice on web front-end development (HTML/CSS/JS) tasks.
Data updated: 2026-10-16 13:02:49 UTC / 2026-10-16 21:02:49 CST (Beijing time)
Top 30
| Rank | Rank Spread | Model | Score | Votes | Price $/M | Context |
|---|---|---|---|---|---|---|
| 1 | 1-1 | claude-opus-5.5-max 1 | 1811 (++15/-15) | 2,597 | $4/$20 | 1M |
| 2 | 2-4 | gpt-6-astra-max 1 | 1780 (++11/-11) | 5,746 | $10/$50 | 1.1M |
| 3 | 2-4 | claude-sonnet-5.5-xhigh 1 | 1774 (++14/-14) | 2,858 | $2/$10 | 1M |
| 4 | 2-5 | gpt-6.1-sol-max 1 | 1760 (++14/-14) | 2,592 | $2/$10 | 1.1M |
| 5 | 4-5 | Claude Fable 5.1 (Max) 1 | 1743 (++9/-9) | 7,230 | $10/$50 | 1M |
| 6 | 6-6 | claude-sonnet-5.5-high 1 | 1713 (++10/-10) | 4,605 | $2/$10 | 1M |
| 7 | 7-10 | Claude Opus 5 (Max) 1 | 1690 (++6/-6) | 17,934 | $5/$25 | 1M |
| 8 | 7-11 | gpt-6-sol-max 1 | 1686 (++11/-11) | 4,032 | $2/$10 | 1.1M |
| 9 | 7-14 | Gemini 4 Argon (High) 1 | 1678 (++15/-15) Preliminary | 1,772 | $2/$10 | 1M |
| 10 | 8-13 | qwen3.8-max-0902 1 | 1673 (++7/-7) Preliminary | 13,081 | $2/$6 | N/A |
| 11 | 7-15 | qwen3.8-max 1 | 1672 (++12/-12) Preliminary | 3,448 | $2/$6 | 1M |
| 12 | 9-15 | Muse Spark 1.3 (Max) 1 | 1659 (++8/-8) | 8,683 | $1.25/$4.25 | 1M |
| 13 | 10-15 | Claude Opus 5 (High) 1 | 1658 (++6/-6) | 23,519 | $5/$25 | 1M |
| 14 | 11-16 | Kimi K3 (Max) 1 | 1655 (++6/-6) | 18,644 | $3/$15 | 1M |
| 15 | 9-20 | Muse Wonder (Max) 1 | 1651 (++18/-18) | 1,228 | $4/$20 | 1M |
| 16 | 14-22 | grok-4.7-xhigh 1 | 1640 (++10/-10) | 4,633 | $2/$6 | 500K |
| 17 | 15-24 | mimo-v2.6-flash 1 | 1635 (++10/-10) | 4,693 | $0.14/$0.28 | 1.1M |
| 18 | 15-24 | qwen3.8-flash-next 1 | 1633 (++8/-8) Preliminary | 7,673 | $0.16/$0.47 | 1M |
| 19 | 15-26 | hy4-preview 1 | 1632 (++10/-10) Preliminary | 4,808 | $0.83/$2.50 | 1M |
| 20 | 15-26 | mimo-v2.6-pro 1 | 1625 (++10/-10) | 4,383 | $0.43/$0.87 | 1.1M |
| 21 | 16-26 | Claude Fable 5 (High) 1 | 1624 (++6/-6) | 15,295 | $10/$50 | 1M |
| 22 | 16-26 | muse-spark-1.3 (xHigh) 1 | 1622 (++8/-8) | 7,987 | $1.25/$4.25 | 1M |
| 23 | 17-26 | glm-5.3-max 1 | 1621 (++8/-8) | 9,125 | $1.40/$4.40 | 1M |
| 24 | 17-28 | deepseek-v4.1-flash-max 1 | 1619 (++11/-11) | 3,544 | $0.30/$1.20 | 1M |
| 25 | 19-28 | grok-4.6-high 1 | 1617 (++8/-8) | 9,774 | $2/$6 | 500K |
| 26 | 19-27 | gpt-5.6-sol-xhigh (codex-harness) 1 | 1617 (++6/-6) | 17,276 | $4/$20 | 1.1M |
| 27 | 24-29 | glm-5.3-flash 1 | 1606 (++7/-7) | 16,470 | $0.05/$0.18 | 1M |
| 28 | 25-29 | glm-5.2-max 1 | 1604 (++6/-6) | 16,093 | $1.40/$4.40 | 1M |
| 29 | 27-35 | qwen3.8-27b 1 | 1594 (++7/-7) | 15,253 | $0.40/$3 | N/A |
| 30 | 29-35 | Gemini 3.7 Flash (High) 1 | 1590 (++7/-7) Preliminary | 11,731 | $0.75/$3.75 | 1M |
How to read this table
- Rank / Rank Spread: relative position estimated from battle votes. The spread shows how far the rank moves within the confidence interval.
- Score: a relative score, useful for comparing the models listed at the same moment.
- Votes / Sessions: sample size. Rankings move more when there are fewer votes.
- Price $/M: reference price per million tokens for input / output.
- Context: maximum context length the model supports.
Three things to check before choosing a model
- Whether the provider actually serves the model, and whether it is available in your region and for your account;
- Whether the API price, rate limits and context window fit your workload;
- Run a small test on three to five real tasks instead of relying on the overall ranking alone.
Data source
Data comes from the Arena AI Code / Web Dev Leaderboard and is refreshed daily by GitHub Actions. For model pricing, licenses and capabilities, check the model provider's own documentation.