Dental-TriageBench: Benchmarking Multimodal Reasoning for Hierarchical Dental Triage

TL;DR

Dental-TriageBench is a new benchmark for multimodal dental triage reasoning, highlighting the challenges and gaps in current models compared to expert clinicians.

Contribution

It introduces the first expert-annotated, multimodal dental triage benchmark with hierarchical labels and reasoning trajectories, enabling better AI system development.

Findings

Models lag behind human experts in fine-grained triage accuracy.

Both complaints and radiographic evidence are essential for accurate triage.

Errors often occur in cases with multiple referral domains, with models producing overly narrow or incomplete referrals.

Abstract

Dental triage is a safety-critical clinical routing task that requires integrating multimodal clinical information (e.g., patient complaints and radiographic evidence) to determine complete referral plans. We present Dental-TriageBench, the first expert-annotated benchmark for reasoning-driven multimodal dental triage. Built from authentic outpatient workflows, it contains 246 de-identified cases annotated with expert-authored golden reasoning trajectories, together with hierarchical triage labels. We benchmark 19 proprietary, open-source, and medical-domain MLLMs against three junior dentists serving as the human baseline, and find a substantial human--model gap, on fine-grained treatment-level triage. Further analyses show that accurate triage requires both complaint and OPG information, and that model errors concentrate on cases with multiple referral domains, where MLLMs tend to produce overly narrow referral sets and omission-heavy errors. Dental-TriageBench provides a realistic testbed for developing multimodal clinical AI systems that are more clinically grounded, coverage-aware, and safer for downstream care.