Best coding models for design
This page uses the WebDev Arena benchmark as a frontend/design signal, then adds current token price, context, and host availability. It is not a general visual-design quality ranking: the benchmark source is an external dataset and remains non-commercial until its upstream licence is confirmed.
| # | Model | WebDev score | Input $/MTok | Output $/MTok | Hosts | Context |
|---|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 1690.6 | $5.00 | $25.00 | 10 | 1.0M |
| 2 | Kimi K3 | 1673.7 | $2.55 | $12.75 | 29 | 1.0M |
| 3 | Qwen3.8 Max | 1668.9 | $2.00 | $6.00 | 2 | 1.0M |
| 4 | Claude Fable 5 | 1626.3 | $10.00 | $50.00 | 10 | 1.0M |
| 5 | GLM 5.3 | 1598.6 | $1.40 | $4.40 | 2 | 1.0M |
| 6 | Qwen3.8 27B | 1594.8 | $0.35 | $2.55 | 20 | 262k |
| 7 | GLM 5.2 | 1593.3 | $0.50 | $2.00 | 66 | 203k |
| 8 | Claude Opus 4.7 | 1566.8 | $5.00 | $25.00 | 10 | 1.0M |
| 9 | Grok 4.5 | 1556.4 | $2.00 | $6.00 | 2 | 500k |
| 10 | Claude Opus 4.6 | 1556.3 | $5.00 | $25.00 | 10 | 1.0M |
| 11 | Claude Opus 4.8 | 1552.2 | $5.00 | $25.00 | 10 | 1.0M |
| 12 | Muse Spark 1.1 | 1539.0 | $1.25 | $4.25 | 2 | 1.0M |
| 13 | Gemini 3.6 Flash | 1527.8 | $0.38 | $1.88 | 4 | — |
| 14 | Claude Sonnet 4.6 | 1522.5 | $3.00 | $15.00 | 10 | 1.0M |
| 15 | Qwen3.7 Max | 1516.7 | $1.48 | $4.42 | 2 | 1.0M |
| 16 | GLM 5.1 | 1508.9 | $0.91 | $2.86 | 44 | 203k |
| 17 | Kimi K2.6 | 1508.7 | $0.55 | $2.52 | 48 | 256k |
| 18 | Gemini 3.5 Flash | 1506.4 | $0.75 | $4.50 | 4 | — |
| 19 | MiniMax M3 | 1487.6 | $0.23 | $0.96 | 28 | 262k |
| 20 | Qwen3.6 Max Preview | 1478.9 | $1.03 | $6.16 | 2 | 262k |
| 21 | MiMo-V2.5-Pro | 1475.7 | $0.30 | $0.61 | 14 | 1.1M |
| 22 | Kimi K2.7 Code | 1472.7 | $0.67 | $3.40 | 35 | 262k |
| 23 | DeepSeek V4 Pro 0423 | 1463.6 | $0.79 | $1.74 | 41 | 1.0M |
| 24 | Qwen3.6 Plus | 1459.7 | $0.33 | $1.95 | 2 | 1.0M |
| 25 | gpt-5.5 (<272K context length) | 1457.5 | $5.00 | $30.00 | 6 | — |