Rankings
Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works
Score and price
| # | Model | Provider | WebDev | Price $/M |
|---|---|---|---|---|
| 1 | Claude Fable 5.2 | Anthropic | 1824 | $8 / $40 |
| 2 | Claude Opus 5.5 | Anthropic | 1819 | $4 / $20 |
| 3 | Claude Sonnet 5.5 | Anthropic | 1772 | $2 / $10 |
| 4 | Gemini 4 Carbon | 1769 | $2 / $10 | |
| 5 | GPT-6.2 Astra | OpenAI | 1766 | $8 / $40 |
| 6 | Gemini 4 Neon | 1765 | $1.50 / $7.50 | |
| 7 | GPT-6 Astra | OpenAI | 1764 | $10 / $50 |
| 8 | GPT-6.2 Sol | OpenAI | 1754 | $2 / $10 |
| 9 | Qwen4-Max | Alibaba | 1751 | $1.50 / $4.50 |
| 10 | GPT-6.1 Sol | OpenAI | 1743 | $2 / $10 |
| 11 | Claude Fable 5.1 | Anthropic | 1742 | $10 / $50 |
| 12 | Muse Wonder Full | Meta | 1723 | Not listed |
| 13 | Gemini 4 Hydrogen | 1701 | $1.50 / $7.50 | |
| 14 | Claude Opus 5 | Anthropic | 1692 | $5 / $25 |
| 15 | GPT-6.1 Terra | OpenAI | 1685 | $1 / $5 |
| 16 | Kimi K3.1 Pro | Moonshot AI | 1683 | $2 / $10 |
| 17 | Gemini 4 Argon | 1682 | $2 / $10 | |
| 18 | GPT-6 Sol | OpenAI | 1674 | $2 / $10 |
| 19 | Qwen3.8-Max | Alibaba | 1674 | $2 / $6 |
| 20 | Kimi K3 | Moonshot AI | 1659 | $3 / $15 |
| 21 | DeepSeek V4.1 Flash | DeepSeek | 1658 | $0.15 / $0.60 |
| 22 | Muse Spark 1.3 | Meta | 1653 | $1.25 / $4.25 |
| 23 | Hy4 | Tencent | 1650 | Not listed |
| 24 | Muse Wonder | Meta | 1647 | $4 / $20 |
| 25 | Inkling 2 Small | Thinking Machines | 1643 | $0.30 / $1 |
| 26 | Grok 4.7 | xAI | 1639 | $2 / $6 |
| 27 | MiMo-V2.6-Flash | Xiaomi | 1638 | $0.14 / $0.28 |
| 28 | Claude Fable 5 | Anthropic | 1626 | $10 / $50 |
| 29 | GLM-5.3 | Z.ai | 1623 | $1.40 / $4.40 |
| 30 | MiMo-V2.6-Pro | Xiaomi | 1622 | $0.43 / $0.87 |
| 31 | Grok 4.6 | xAI | 1618 | $1.60 / $4.80 |
| 32 | GPT-5.6 Sol | OpenAI | 1615 | $4 / $20 |
| 33 | GLM-5.3-Flash | Z.ai | 1610 | $0.02 / $0.07 |
| 34 | Muse Ember | Meta | 1608 | $0.10 / $0.50 |
| 35 | Claude Haiku 5.5 | Anthropic | 1595 | $0.10 / $0.50 |
| 36 | Qwen3.8-27B | Alibaba | 1590 | $0.40 / $3 |
| 37 | Gemini 3.7 Flash | 1589 | $0.75 / $3.75 | |
| 38 | Gemini 3.8 Flash | 1584 | $0.75 / $3.75 | |
| 39 | GPT-6 Luna | OpenAI | 1578 | $0.10 / $0.50 |
| 40 | Mistral Large 4 | Mistral | 1573 | $0.70 / $2.10 |
| 41 | Step 5 Preview | StepFun | 1570 | $1 / $2.70 |
| 42 | Claude Opus 4.8 | Anthropic | 1555 | $5 / $25 |
| 43 | Claude Sonnet 5 | Anthropic | 1539 | $2 / $10 |
| 44 | Beam 1.0 | Reflection AI | 1437 | $0.30 / $1 |
Other benchmarks
Frequently asked questions
What does WebDev Arena measure?
Head-to-head votes from developers who ask two anonymous models to build the same web app and pick the better result. Votes are turned into an Elo-style rating.
Which model has the highest WebDev Arena score?
Claude Fable 5.2 from Anthropic leads WebDev Arena at 1824, ahead of Claude Opus 5.5 (1819).
Why does WebDev Arena matter to engineering leaders?
It captures what engineers actually prefer when they look at working output, including UI quality and following the brief, which pass/fail tests miss.
What are the limitations of WebDev Arena?
Preference votes favour visually polished front-end work and say little about back-end or infrastructure code. New models carry wider confidence intervals until they collect votes.