FaithfulBench: Does AI Counsel Uphold or Undermine the User's Professed Faith?

Naming the faith wins a faithful first answer but not steadfastness; the guide improves both. It comes from a paper posted to arXiv on 15 September 2026. Do AI assistants help believers reason about moral dilemmas consistently with their faith? We present FaithfulBench, the first benchmark to score AI counsel across traditions by how well it adheres to the user's professed faith. Scenarios are drawn from each tradition's most respected texts, with the faithful answer known and applied by the judges as the standard. We test five frontier models under three conditions: the AI does not know the user's tradition; it receives a one-line prompt identifying the user as a practicing adherent; or it receives a companion-counselor guide rooted in the tradition's sources. Two judges score the initial response and whether the model caves or holds when pressured toward the answer the user wants. When the tradition is unstated, models counsel from a secular therapeutic default and every model fails some believers.

Why it counts

Naming the faith wins a faithful first answer but not steadfastness; the guide improves both. We present FaithfulBench, the first benchmark to score AI counsel across traditions by how well it adheres to the user's professed faith.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.