LLM Leaderboard

Compare how different large language models perform at writing Clerk code and select the one that best fits your requirements.

Model / Average	Organizations	Billing	Webhooks	Add Auth	Auth	Machine Auth	Quickstarts	UI Components	User Management
1 DeepSeek V4.1 Flash 92%	95%	90%	81%	100%	95%	100%	87%	78%	100%
2 Claude Sonnet 5.5 92%	95%	90%	81%	100%	98%	100%	88%	73%	100%
3 Claude Fable 5.1 92%	89%	90%	82%	100%	93%	100%	88%	83%	100%
4 Claude Opus 5 91%	92%	87%	78%	100%	91%	100%	87%	88%	100%
5 Claude Opus 5.5 91%	92%	85%	77%	100%	95%	100%	90%	81%	100%
6 GPT-5.6 Terra 91%	86%	93%	88%	100%	91%	100%	88%	71%	100%
7 GPT-6 Astra 91%	92%	92%	82%	100%	98%	100%	88%	71%	92%
8 Claude Fable 5 90%	86%	88%	79%	100%	96%	100%	85%	81%	100%
9 Tencent Hy4 Preview 90%	92%	90%	74%	100%	93%	100%	87%	76%	100%
10 GPT-5.6 Sol 90%	84%	95%	88%	100%	92%	100%	85%	76%	92%
11 Kimi K3 90%	86%	85%	82%	100%	96%	100%	82%	80%	100%
12 GPT-6.1 Sol 90%	92%	95%	85%	91%	93%	100%	88%	73%	92%
13 Gemini 3.8 Flash 90%	92%	88%	81%	100%	96%	100%	89%	71%	92%
14 GPT-5.6 Luna 90%	89%	93%	91%	100%	87%	100%	86%	71%	92%
15 GPT-6 Sol 90%	87%	95%	85%	100%	94%	100%	86%	69%	92%
16 Gemini 3.6 Flash 89%	83%	88%	75%	82%	96%	100%	89%	85%	100%
17 Gemini 3.7 Flash 88%	81%	88%	85%	100%	96%	100%	87%	74%	83%
18 GPT-6 Luna 86%	84%	90%	88%	100%	92%	90%	84%	59%	92%
19 Claude Sonnet 5 86%	83%	86%	74%	82%	93%	100%	82%	71%	100%
20 Gemini 3.1 Pro Preview 85%	91%	88%	61%	82%	91%	100%	87%	66%	100%
21 Grok 4.6 84%	59%	90%	88%	100%	94%	100%	47%	78%	100%
22 GLM 5.3 Flash 83%	86%	86%	68%	73%	92%	100%	82%	69%	92%
23 Gemini 3.5 Flash-Lite 80%	71%	87%	66%	82%	93%	100%	60%	69%	92%
24 Grok 4.5 73%	86%	86%	88%	0%	96%	100%	32%	78%	92%
25 Grok 4.7 60%	86%	77%	77%	0%	78%	0%	55%	68%	100%

Last updated: September 30, 2026

Trusted by fast-growing companies around the world.