Clerk LLM Leaderboard: leaderboard
Evaluates LLMs on writing Clerk authentication and user management code across 7 categories: Organizations, Billing, Webhooks, Authentication, Quickstarts, UI Components, and User Management.
Metric: Avg score (%). Source: clerk.com. Saturation forecast: Estimated already saturated. 25 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4.1 Flash | 92 | #36 |
| 2 | Claude Fable 5.1 | 91.7 | #9 |
| 3 | Claude Sonnet 5.5 | 91.7 | #11 |
| 4 | Claude Opus 5 | 91.5 | #12 |
| 5 | Claude Opus 5.5 | 91.1 | #3 |
| 6 | GPT-5.6 Terra | 90.8 | #41 |
| 7 | GPT-6 Astra | 90.5 | #6 |
| 8 | Claude Fable 5 | 90.5 | #16 |
| 9 | Hy4 preview | 90.3 | #38 |
| 10 | GPT-5.6 Sol | 90.2 | #19 |
| 11 | Kimi K3 | 90.1 | #30 |
| 12 | Gemini 3.8 Flash | 90 | #21 |
| 13 | GPT-6.1 Sol | 90 | #7 |
| 14 | GPT-5.6 Luna | 89.9 | #68 |
| 15 | GPT-6 Sol | 89.7 | #14 |
No result here: #8 Gemini 4 Argon, #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=clerk-llm-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.