Five of fourteen models named WorkOS AuthKit first on the direct prompt; zero named Clerk. WorkOS AuthKit was named by twelve of the fourteen models and Clerk by ten and WorkOS AuthKit carries 29 labels and Clerk 23, so the shares are not directly comparable.
Named in two categories this edition.
Named in two categories this edition.
Share is the count of first choices across the direct, paraphrase, budget and scale prompts over all fourteen models, for a mid-market B2B company; rank is within the category; every quote names the model and the prompt it came from. Both figures come from the customer identity and access management page.
Across every category in the November 2026 Edition, WorkOS AuthKit and Clerk were named in the same answer thirty-nine times, of the 87 answers naming WorkOS AuthKit and the 84 naming Clerk. In those answers Clerk took the first choice fourteen times and WorkOS AuthKit ten.
| Model | Direct | Paraphrase | Comparative | Budget-constrained | Scale-constrained | Negative |
|---|---|---|---|---|---|---|
| Claude Haiku 4.5 | ||||||
| GPT-5.4 mini | ||||||
| Gemini 3.5 Flash | ||||||
| Perplexity Sonar | ||||||
| Grok 4.20 | ||||||
| Mistral Small | ||||||
| DeepSeek V4 Flash | ||||||
| Llama 4 Maverick | ||||||
| Qwen 3.7 Flash | ||||||
| Kimi K2 | ||||||
| GLM 4.7 FlashX | ||||||
| MiniMax M2.5 | ||||||
| GPT-6 Luna | ||||||
| Muse Glimmer 30B |
Bold names in an answer are the products the judge labeled a first choice; a model naming several gives each of them that label. The full answer text for every row is in the record.
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“WorkOS documented a major service disruption on July 16, 2026 with elevated latency, timeouts, and 5xxs across AuthKit, SSO, and user-management flows.” GPT-5.4 mini · negative prompt · soft negative
“a massive drop in recommendation acceptance for platforms like WorkOS (falling from 22% to 4%)... such a sharp deviation warrants close scrutiny” Qwen 3.7 Flash · negative prompt · soft negative
“Modern developer-first options with good UX, but verify their long-term viability and security maturity” DeepSeek V4 Flash · negative prompt · soft negative
“WorkOS stands out as the best customer identity and access management (CIAM) platform for most mid-market B2B companies” Grok 4.20 · direct prompt · first choice
“Best Overall for Modern B2B SaaS: WorkOS ... is often the top recommendation.” Gemini 3.5 Flash · paraphrase prompt · first choice
“WorkOS – *Best Overall for Enterprise Readiness & Developer Experience*” Gemini 3.5 Flash · direct prompt · first choice
Every negative label with a quote, up to three, then the highest-weighted positives, up to three. Six of seven in this category shown.
“Clerk's own postmortems show that outages in one service can cascade into session-management downtime, and Clerk notes its session service incidents can cause "complete downtime" for customers.” GPT-5.4 mini · negative prompt · soft negative
“Clerk or similar developer-first tools as your only enterprise CIAM. Be cautious if you need mature consent management” Perplexity Sonar · negative prompt · soft negative
“Modern developer-first options with good UX, but verify their long-term viability and security maturity” DeepSeek V4 Flash · negative prompt · soft negative
“Clerk has become the go-to recommendation for modern startups building web apps” Qwen 3.7 Flash · budget prompt · first choice
“Best Overall Value: Clerk” Kimi K2 · budget prompt · first choice
“Developer‑centric teams building modern consumer apps favor Auth0, Clerk, Supabase Auth, Firebase Auth, Descope, Frontegg” GLM 4.7 FlashX · comparative prompt · alternative
Comparisons are drawn for the top eight products in each category, each against each. The output is the models' output; nothing here is a recommendation by the index.